Skip to content
Artwork for Daily Paper Cast
ScienceTechnology

Daily Paper Cast

Jingwen Liang, Gengyu Wang

We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers). Both the podcast scripts and audio are generated by AI. Feedback and suggestions are welcome! Email us: dailypapercast.ai@gmail.com

Creator:
Jingwen Liang, 3D ML, https://www.linkedin.com/in/jingwen-liang/
Gengyu Wang, LLM ML, http://wanggengyu.com

Listen on:
Spotify: https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXL
Apple Podcast: https://podcasts.apple.com/us/podcast/daily-paper-cast/id1777620236

Cover Image by Kawen Kuang https://kawen.art

Play
  • 360 episodes
  • Avg 21 min
  • English
Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.
  • #2522
    Today · 22 min

    Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices

    🤗 Upvotes: 61 | cs.OS Authors: Yifei Wang, Tsun-yu Yang, Yechen Xu, Hancheng Ye, Qinsi Wang, Baijun Zhou, Tingjun Chen, Hai "Helen" Li, Danyang Zhuo, Yiran Chen Title: Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices Arxiv: http://arxiv.org/abs/2611.14848v1 Abstract: Large language model (LLM) agents are rapidly becoming a dominant paradigm for AI applications. Recently, there is a growing demand to deploy large-scale Mixture-of-Experts (MoE) models locally on consumer PCs to balance data privacy, API costs, and inference efficiency. However, unlike datacenter servers with abundant DRAM, consumer devices are tightly constrained in both GPU VRAM and host RAM, forcing massive MoE weights to spill across VRAM, host RAM, and SSD. Under such spilling, we observe that existing systems fail to fully utilize this memory hierarchy, treating the tiers as independent caches and thrashing in inference. We present TIDEWAY, a system for efficient inference of large MoE models on memory-constrained consumer devices. Our core insight is to manage host RAM and GPU VRAM as a unified memory pool. Within this pool, TIDEWAY couples phase-aware memory layouts, which adapt to the distinct access patterns of prefill and decode, with an execution engine that optimizes CUDA Graph execution under expert paging. Our evaluations on representative consumer hardware with frontier MoE models demonstrate that TIDEWAY significantly outperforms state-of-the-art systems. On average, TIDEWAY achieves speedups of 1.97x in end-to-end latency and 2.40x in Time-to-First-Token (TTFT), along with 1.61x higher decode throughput against the fastest baseline. Our source code is publicly available at https://github.com/Afterglow231/Tideway .

    • Transcript
  • #2521
    Today · 21 min

    Jeveration: System One Models Now Generate

    🤗 Upvotes: 45 | cs.CV Authors: Yuhe Liu, Qi Li, Shihua Zhang, Xinchao Wang Title: Jeveration: System One Models Now Generate Arxiv: http://arxiv.org/abs/2611.24738v1 Abstract: System One models such as Jev return decisions through fast, parallel prediction. In this paper, we introduce Jeveration, showing that the same decision paradigm can also generate high-quality images in a single forward pass. Jeveration builds on a frozen vision-language model, repurposing its visual-semantic knowledge for holistic image generation. The key challenge is to maintain global consistency. A single prompt admits many valid images, yet parallel predictions must converge on a coherent whole. We therefore condition all positions on a shared random state to coordinate parallel predictions, so that each draw yields a different but coherent image. Since the model tends to ignore this state under direct image supervision, we first learn a distribution over discrete image codes to guide single-pass generation. Beyond text-to-image generation, we further unify image-to-image generation and dense prediction within the same architecture, so that one checkpoint supports all three tasks, each in one forward pass. Experiments show that Jeveration generates a 512x512 image in 78 ms, up to 122x faster than existing unified models, while maintaining competitive image quality and dense prediction performance.

    • Transcript
  • #2520
    Today · 23 min

    PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling

    🤗 Upvotes: 26 | cs.LG, cs.AI Authors: Minseo Yoon, Minseong Bae, Sojin Lee, Hyunwoo J. Kim Title: PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling Arxiv: http://arxiv.org/abs/2611.11318v1 Abstract: High-resolution weather prediction is important for resolving local atmospheric patterns missed by coarse global forecasts. Large pretrained weather backbones have improved global forecasting, but adapting them to produce future high-resolution fields from recent coarse states remains challenging and costly. We formulate this setting as Predictive Spatiotemporal Weather Downscaling (PSWD), a task that jointly refines spatial and temporal resolution while predicting future high-resolution trajectories. To this end, we propose a framework that decomposes prediction into spatial and temporal stages using a shared pretrained backbone, fixed numerical scaffolds, and lightweight residual heads. For backbone adaptation, we introduce PROLA (PRincipal-Orthogonal Low-rank Adaptation), which allocates a fixed low-rank budget between pretrained weights' principal directions and their orthogonal complement. PROLA further rescales rank-1 optimizer updates using gradient signals, improving adaptation without increasing trainable rank. Experiments in the PSWD setting show that PROLA outperforms representative low-rank adaptation baselines. Further experiments across diverse datasets and tasks support the broader applicability of PROLA, showing that its benefits extend beyond the primary weather downscaling setting.

    • Transcript
  • #2519
    Today · 20 min

    Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development

    🤗 Upvotes: 22 | cs.CV Authors: Xirui Jiang, Yuxi Chen, Rui Yang, Feng Luo, Pengcheng Wang, Bingxuan Li, Zihao Zhao, Yushan Li, Han Wang, Manling Li, Yang Zhang, Shiyu Chang, Tong Zhang, Huan Zhang Title: Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development Arxiv: http://arxiv.org/abs/2611.24154v1 Abstract: Games are a rich testbed for visual agents, demanding perception, long-horizon planning, and precise control. However, collecting human gameplay is costly, and learning from gameplay videos requires inferring missing actions. Existing datasets also cover a limited range of games, often without explicit tasks or verifiable outcomes. To address these gaps, we introduce Game2Player, a framework that co-develops game environments and players to collect diverse and verifiable gameplay experience at scale. In the Game2Player loop, a Builder agent adapts existing web games, exposes their internal state, and defines tasks with state-based progress measures and success checks. A Coding Player and a VLM Player then attempt the tasks and report problems to the Builder for repair, so that play serves as both environment validation and training data collection. With Game2Player, we build 568 verified web games with 3,436 tasks, collect 15.7K trajectories (307 hours of gameplay), and hold out 50 games as the benchmark PlayerBench. To evaluate the collected experience as training data, we train VLM agents with progress-weighted SFT, assigning greater weight to steps that advance task progress. Game2Player-9B improves progress from 14.3% to 31.2% on PlayerBench and from 30.0% to 53.1% on the external GameWorld benchmark. More broadly, our work suggests a path for visual agents to scale their gameplay experience by building, verifying, and learning from existing game worlds.

    • Transcript
  • #2518
    Yesterday · 20 min

    TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks

    🤗 Upvotes: 143 | cs.AI Authors: Xingchen AGI Lab, Baotian Hu, Bingkai Yang, Boyang Wang, Changzai Pan, Chao Lyu, Chao Wang, Chen Li, Chenshuo Pan, Chenyu Lin, Chenyuan Zhang, Chongming Liu, Dawei Fan, Di Wu, Dong Guo, Dong Li, Dongfang Li, Enlin Liu, Fanye Xiao, Fengkai Li, Fubei Yao, Gang Lin, Han Gao, Hanming Wu, Haowei He, Huapeng Liu, Hua Wang, Huinan Xu, Jiahong Xiong, Jiaxin Peng, Jianxiang Ma, Jianxing Zhuge, Jie Zhang, Ji Xiong, Jinglin Chen, Jingqi Li, Jingxuan Li, Jiwang Ye, Junchen Li, Junbiao Li, Junyang Wu, Kaidong Yu, Kaipeng Jia, Kehai Chen, Kuai Li, Laobin Liu, Lei Li, Libo Qin, Lingling Shi, Luwen Pu, Menghao Xu, Mengjiao Bao, Mengqi Chen, Min Zhang, Mingrui Wang, Naying Wang, Peicong Han, Peiming Guo, Pengfei Li, Qiang Feng, Qi Wang, Qingjun Zhu, Qingli Li, Qitai Ding, Qiyi Xie, Quanchao Zhao, Rongbao Han, Rui Xue, Ruiyu Fang, Ruiting Song, Shijie Li, Shiquan Wang, Shuangyong Song, Sishi Xiong, Teng Su, Wankang Bao, Weijie Zhang, Wei Mao, Weiwei Fu, Weiyang Huang, Wenmin Deng, Wenqing Hu, Wujie Zhong, Xi Yu, Xiaohui Hu, Xiaomin Fang, Xiaomeng Huang, Xiaoqiong Shi, Xiaotong Shang, Xiaoyu Li, Xinglei Xu, Xin Jiang, Xin Wang, Xin Zhang, Xinzhang Liu, Xue Liu, Xuefeng Bai, Xuewei He, Yahan Li, Yanhan Zhang, Yanlei Xue, Yanzhang Wu, Yang Yu, Yi Liu, Yin Zhang, Yingyan Li, Yitong Yao, Yixuan Li, Yongqiang Xia, Yongxiang Li, Yinzhou Zhu, Yu Zhao, Yuhao Jiang, Yunpeng Zhang, Yuting Lin, Yuxuan Wu, Yuyao Huang, Yuyi Wang, Zebo Peng, Zhenwu Pei, Zhenxiong Li, Zhao Wang, Zhaoxi Zhang, Zhihao Yang, Zhiqiang Dong, Zhiwei Yan, Zhilong Lu, Zhonghao Guo, Zhongheng Wu, Zhongjiang He, Zhongqiu Li, Zhu Yuan, Zhuoru Jiang, Zhuoyi Wei, Zijia Guo, Zilu Huang, Zhipeng Guo, Zirui Li, Zihan Wang, et al. (39 additional authors not shown) Title: TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks Arxiv: http://arxiv.org/abs/2611.22115v1 Abstract: We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning architecture selection, large-scale pretraining, and reasoning and agentic post-training. We study how sparse activation, attention design, model depth and width, and speculative decoding balance model capacity with computation, memory access, and execution overhead. Our pretraining infrastructure builds on MindSpore HyperParallel, combining topology-aware hybrid sharding, efficient distributed optimizer execution, and coordinated management of long-sequence workloads and activation memory. CPU affinity and core isolation further reduce host scheduling interference. Together, these mechanisms support the pretraining of a 285B-parameter model on 8,192 Ascend 910C cards, providing a concrete setting for the architectural and systems studies. For post-training, we introduce TeleGym, a unified agent execution platform that connects execution, evaluation, and trajectory construction to policy optimization. Disaggregated asynchronous execution, bounded oversampling, and partial rollout accommodate heterogeneous task durations while preserving trajectory continuity across policy updates. Together, these advances establish an Ascend-oriented training foundation for the continued development of Xing 4 across model scales and increasingly demanding reasoning and agent workloads.

    • Transcript
  • #2517
    Yesterday · 22 min

    AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs

    🤗 Upvotes: 88 | cs.AI, cs.DC, cs.LG Authors: AI Training Platform Team, Bingwei Zhang, Jing Li, Amir Abdullin, Sihang Chen, Xin Chen, Liangjun Feng, Yingmeng Gao, Tao Guo, Junjie Huang, Dongfang Li, Zhanglian Lin, Jiajun Liu, Zekun Liu, Zhengxuan Lu, Xiaodong Luo, Jian Meng, Ivan Nosov, Linyuan Qiu, Weijian Sun, Wanrui Yan, Binfan Zheng, Zhicheng Zhou, Baotian Hu, Min Zhang, Haizhou Li, Zhiquan Luo Title: AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs Arxiv: http://arxiv.org/abs/2611.17621v1 Abstract: Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to optimize existing implementations under input configurations drawn from real workloads. To address this requirement, we introduce AscendGYM, a benchmark whose initial suite comprises 48 kernels across three difficulty levels. Each kernel is paired with test cases whose data types and tensor shapes are collected from real-world training and inference tasks. Consequently, performance improvements on AscendGYM map directly to the corresponding workloads. In terms of usability, two evaluation modes are supported in AscendGYM: model evaluation and model-harness evaluation. The kernel optimization capabilities of both trained models and custom agents are allowed to be measured. It provides a complete execution environment that closely reproduces how Ascend kernels are invoked in practical pipelines. For model evaluation, it additionally includes a built-in harness equipped with search orchestration and experience accumulation. Finally, we propose a new metric, the Speedup-Token Score (STS), which quantifies performance gains relative to token cost. By jointly considering speedup and cost, STS enables the assessment of practical kernel optimization capability of a model or harness under an acceptable budget. AscendGYM is available at https://github.com/SLAI-AITP/AscendGYM.

    • Transcript
  • #2516
    Yesterday · 21 min

    Weight-Space Programming Doesn't Need Transformers

    🤗 Upvotes: 40 | cs.LG, cs.AI, cs.CL Authors: Hyunjong Ok, Jaeho Lee Title: Weight-Space Programming Doesn't Need Transformers Arxiv: http://arxiv.org/abs/2611.22055v1 Abstract: Standard neural architectures such as the Transformer were chosen because they train well with gradient descent and run fast on GPUs. In weight-space programming, a large language model (LLM) writes target weights by hand without gradient-based training, so those reasons no longer apply. Should we keep the Transformer? Given minimal guidance, ten labeled examples, and a sandbox, mainly on multiple-choice questions, we task three frontier LLMs with either generating the weights of a fixed architecture or designing the architecture themselves. When free to design, all three compile plain-text facts into a sparse table queried by a fixed procedure, reaching up to 54.4% test accuracy. An LLM-designed model achieves higher test accuracy than the most accurate released Transformer that the same LLM wrote while using about 1,800x fewer parameters. Without gradients, they choose a table, in which the LLM can state what each weight means and can find and rewrite a wrong one. Each wrong answer points to one row, and removing a row changes about one other answer. From this, we propose an associative-memory-based model up to 17x faster on GPUs than a same-sized Transformer. We also test pretrained weights, other benchmarks, and tasks where models generate answers. Pretrained LLMs remain more accurate; the claim concerns which structure to build when writing weights.

    • Transcript
  • #2515
    Yesterday · 22 min

    ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models

    🤗 Upvotes: 39 | cs.RO Authors: Ke Sun, Kevin Yuchen Ma, Yike Zhang, Yanzhe Chen, Mike Zheng Shou Title: ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models Arxiv: http://arxiv.org/abs/2611.21099v1 Abstract: Frontier multimodal models can now control robots zero-shot from images, yet many manipulation tasks depend on contact forces that images cannot show. Bringing force to an API-only frozen model raises two challenges. First, contact evolves much faster than an API model can decide, so the system must close the loop on force beneath the model. Second, a frozen model cannot interpret raw force streams, so force must be returned in a form the model can reason about. Therefore, we present ForceHarness, a harness that lets frozen models use force without demonstrations or finetuning. After calibrating hand force from a wrist sensor or joint torques alone, ForceHarness addresses the first challenge with self-terminating force primitives that regulate force on their own and return at a contact event. To address the second challenge, a physics translation layer turns each force trace into physical quantities with uncertainty as the tool result. To evaluate ForceHarness against expert force controllers and learned policies under identical conditions, we also build HiddenPhys, a seven-task MuJoCo benchmark with hidden physical variables. On a real arm without a wrist force sensor, ForceHarness raises the zero-shot success rate of GPT-6 Astra from 3.3% to 90.0%. In simulation, it adds 17.5 percentage points on the public ForceBench suite and 34.3 percentage points on HiddenPhys, surpassing force-aware policies trained on demonstrations on both benchmarks and matching hand-written expert controllers on HiddenPhys. Ablations further show that smaller models make significantly better decisions when given physical quantities rather than raw force values.

    • Transcript
  • #2514
    Yesterday · 22 min

    Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose

    🤗 Upvotes: 33 | cs.LG, cs.AI Authors: Ivan Poddiakov, Ivan Kruzhilov, Galina Zubkova, Svetlana Erofeeva, Andrey Savchenko, Pavel Blinov Title: Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose Arxiv: http://arxiv.org/abs/2611.15348v1 Abstract: Electronic nose (eNose) technology offers a portable, non-invasive route for disease screening via exhaled breath analysis. However, progress in the field is hindered by the lack of systematic benchmarks that compare machine learning methods under realistic conditions, particularly sensor drift, a known but rarely quantified failure mode. Most existing studies rely on small, private datasets with inconsistent protocols, rendering results non-comparable and slowing progress. We introduce Breath-Dx, the first comprehensive benchmark of time series classification methods for breath-based disease screening. Our work leverages the Scent of Health (S-OH) dataset, the largest public clinical eNose collection to date, comprising 1,234 patients across nine diagnostic groups, each providing a 17-channel multivariate time series with explicit temporal train/test splits that account for sensor drift. We systematically evaluate 10 methods spanning four families: feature-based tabular learners, convolution-based models, graph-based, and time series architectures. All methods degrade significantly under temporal validation (0.05-0.12 AUC drop compared to random cross-validation), confirming that drift embeds a strong temporal signal. Under this realistic evaluation, the best methods achieve ROC AUC of 0.74-0.76 for some lung conditions, though others remain near chance. Recurrent architectures show the most consistent performance across diseases, while specialized time series methods achieve the highest peak results. Demographic confounders matter: breath signals provide independent diagnostic value for some conditions but add little beyond age for others. We release the S-OH dataset, all temporal splits, evaluation protocols, and code to enable reproducible research and accelerate progress in clinical breathomics.

    • Transcript
  • #2513
    Yesterday · 23 min

    Multi-Branch Transformer

    🤗 Upvotes: 31 | cs.LG, cs.CL Authors: Gaotang Li, Lingjie Chen, Chunyuan Deng, Zhiwei Xu, Hongzheng Chen, Christopher De Sa, Jingrui He, Yingheng Wang, Hanghang Tong Title: Multi-Branch Transformer Arxiv: http://arxiv.org/abs/2611.19800v1 Abstract: Transformer language models are commonly scaled by making their blocks wider or stacking them deeper. In this work, we explore a complementary path: branching, the parallel composition of full Transformer blocks. We introduce the Multi-Branch Transformer (MBT), which processes the input through shared initial layers, executes independently parameterized branches of sequential blocks in parallel, and fuses their outputs before shared final layers. At comparable training compute, we study three MBT variants: Wide-Shallow preserves block width, Narrow-Deep preserves sequential depth, and Balanced interpolates between them. In controlled pretraining experiments at four mixture-of-experts scales (0.8B to 2.1B total parameters), 2-branch Wide-Shallow MBTs consistently outperform sequential Transformers under matched parameter and training-compute budgets. Balanced MBTs improve further and retain comparable quality as the number of branches increases. To improve inference efficiency at long contexts, we introduce Joint-KV, which constructs a shared KV cache from branch representations at each depth. Our final recipe combines Balanced MBTs with Joint-KV, supported by an inference engine that exploits branch grouping and shared-cache reuse. Fitted scaling curves indicate that standard Transformers require up to 1.26x as much training body compute to match our final models' validation loss. These models reduce full-model KV-cache storage by up to 34% and deliver up to 51.4% higher decoding throughput on a single H200 GPU. Ablation studies show that branching yields gains beyond changes in width and depth, enables an effective KV-sharing strategy (Joint-KV), remains robust across fusion functions, and performs best in the middle layers. These findings show that branching offers a practical path for scaling language models toward both better modeling quality and faster inference.

    • Transcript
  • #2512
    Yesterday · 23 min

    Self-Improvement Memory Enables Continual Recursive Self-Improvement

    🤗 Upvotes: 26 | cs.LG, cs.AI Authors: Xin Yu, Fei Xia, Jiaqi Pan, Youbao Tang, Chengzhi Liu, Adams Yu, Sicong Jiang, Yanfei Chen, Lingzhou Xue, Ting Yu Title: Self-Improvement Memory Enables Continual Recursive Self-Improvement Arxiv: http://arxiv.org/abs/2611.18856v1 Abstract: Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this work, we study Continual Recursive Self-Improvement (CRSI), a setting for continuing existing harness-optimization methods across compatible benchmarks or policy models. We propose Self-Improvement Memory (SIM) for the harness optimizer, rather than the task-solving policy. SIM groups edits by recurring harness problem and records their rationale, predicted and observed outcomes, and evaluation context. New attempts extend this history as optimization continues. In our experiments across four domains, SIM achieves higher final scores than harness-only and root-cause-only continuation in cross-dataset and pairwise cross-model comparisons. Across ten independent source runs in coding, paired continuations with SIM improve final scores by an average of 2.36 points over harness-only continuation ($p=0.003$).

    • Transcript
  • #2511
    Yesterday · 20 min

    TCP4D: A Unified Tool-Center-Point Tracking and Generation Model for Robot Manipulation

    🤗 Upvotes: 23 | cs.RO, cs.CV Authors: Haosong Peng, Xiangyang Liu, Zhengshen Zhang, Yunfeng Fan, Tianyu Qi, Xin Xia, Yufeng Zhan, Wenchao Xu Title: TCP4D: A Unified Tool-Center-Point Tracking and Generation Model for Robot Manipulation Arxiv: http://arxiv.org/abs/2611.23143v1 Abstract: Robot manipulation videos provide a rich visual experience, yet recovering robot action and gripper-state annotations from RGB observations still remains challenging. Using the embodiment-agnostic tool-center-point (TCP) pose as the action space, we present TCP4D, a unified model in which a shared 4D scene representation both tracks observed TCP motion and generates future TCP trajectories. Given a monocular video and initial 2D TCP queries, the tracker directly recovers metric TCP poses in SE(3) and gripper states alongside scene geometry and camera parameters. The generator samples local features from the same 4D representation along the recovered TCP tracks, then combines them with robot observations and language instructions to predict future TCP states. Our new cross-embodiment augmentation pipeline converts existing RGB videos into demonstrations for alternative embodiments by retargeting the recovered motion and synthesizing the corresponding observations, without recorded source-robot states. Experiments show that the tracker achieves absolute trajectory errors of 7.60 and 16.07 mm on DROID and RoboLab and adapts to a new embodiment with only ten demonstrations. The generator achieves 69.19% mean success on RoboTwin and outperforms well-established policy models on two real-world tasks, while joint training on source and augmented demonstrations improves target-robot success by 41.5% over augmented-only training.

    • Transcript
  • #2510
    Tuesday · 21 min

    AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data

    🤗 Upvotes: 48 | cs.LG, q-fin.TR Authors: Annan Wang, Yuchen Xie, Yu Cen, Leon Liangyu Chen, Qianyu Julie Zhu, Xin Li, Tianyi Wei, Weisi Lin Title: AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data Arxiv: http://arxiv.org/abs/2611.19937v1 Abstract: Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportunities. However, traditional pipelines often decouple signal forecasting from portfolio construction, potentially misaligning learning with allocation and execution objectives. We present AllocFlow, an end-to-end flow-matching framework that directly generates joint portfolio allocations from raw multi-asset market histories. To capture dependencies among portfolio positions, AllocFlow employs a cross-asset flow Transformer conditioned on temporal market representations to generate continuous, signed position weights across all instruments jointly. To address the sample inefficiency and instability of learning continuous allocation policies from scratch, we establish a two-stage training scheme: strategy-supervised imitation shapes a structured distribution of candidate portfolios, followed by group-relative reinforcement learning (RL) that refines joint decisions using portfolio-level financial rewards and a frozen policy reference. On hourly cryptocurrency perpetual futures, RL refinement raises the annualized net return of the imitation policy from $27.79\%$ to $51.38\%$ and its Calmar ratio from $0.955$ to $4.043$, surpassing the teacher strategy on every metric, and AllocFlow reaches a Calmar ratio of $4.90$ on six further months of unseen 2026 data without retraining.

    • Transcript
  • #2509
    Tuesday · 24 min

    InclusionMed: Benchmarking AI for Inclusive Healthcare

    🤗 Upvotes: 39 | cs.AI Authors: InclusionMed Collaboration Title: InclusionMed: Benchmarking AI for Inclusive Healthcare Arxiv: http://arxiv.org/abs/2611.21218v1 Abstract: Advancing medical AI for inclusive healthcare requires evaluation across diverse healthcare roles, tasks, and care settings, but benchmark coverage remains uneven. We introduce InclusionMed, an open medical AI evaluation initiative for inclusive healthcare. The InclusionMed Atlas organizes benchmarks across three healthcare roles and three AI capabilities. For the first release, we selected four public benchmarks from 388 candidates through structured audits and independent reproduction. With InclusionMed-DxFiles, our private diagnostic reasoning benchmark, the Atlas contains five benchmarks covering three of its nine role--capability cells. We evaluated frontier large language models on the Atlas and aggregated their results into the InclusionMed Index, with overall scores ranging from 17.5 to 49.1 out of 100. The Index also reports scores by healthcare role and AI capability, showing that a model's rank varied with the role or capability considered. A within-benchmark analysis using task-level tags showed that the ten highest-ranked models in the Index all scored higher on patient communication than on clinical decision-making. Models with similar Index scores also differed substantially in estimated inference cost. These findings highlight the need for evaluation covering more diverse healthcare needs and for context-specific model selection. Through open collaboration and community contributions, InclusionMed seeks to ensure that diverse healthcare needs worldwide shape how medical AI progress is defined and measured.

    • Transcript
  • #2508
    Tuesday · 22 min

    Sage S2.1 Flash Technical Report

    🤗 Upvotes: 36 | cs.AI Authors: Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu, Tao Gui, Honglin Guo, Yuyang Hu, Zixian Huang, Jiajie Jin, Alexander Lam, Jiaqiang Li, Yining Li, Jiahang Lin, Yanjiang Liu, Xinyu Lu, Haijun Lv, Ningsheng Ma, Zerun Ma, Minlong Peng, Jianmin Qian, Huayu Sha, Junlin Shang, Shuo Shen, Qisheng Su, Jiajun Sun, Yanan Sun, Zhichao Sun, Ran Tao, Zhongbo Tian, Guoqiang Wang, Hui Wang, Rui Wang, Yiding Wang, Zhecan Wang, Hao Xiang, Xinchen Xie, Shuhao Xing, Xiaoyu Xing, Wanghan Xu, Xinyu Yang, Yajie Yang, Dingbo Yuan, Yuhang Zang, Hongjie Zhang, Chengfeng Zhao, Haoran Zhao, Penghao Zhao, Ruojun Zhou, Dongsheng Zhu, Yicheng Zou, Qiye Cai, Yifei Cao, Xinmeng Che, Hongji Chen, Jiabei Chen, Jiadong Chen, Jiahao Chen, Jiayi Chen, Xinjie Chen, Yujia Chen, Xin Deng, Yi Dong, Yichen Dong, Wenjie Fu, Jianing Geng, Chenyang Gu, Ding Han, Han Han, Feiyang Hao, Haotan He, Qiushi He, Xufeng He, Xin Hong, Jie Hou, Binze Hu, Yongkang Hu, Zijian Hu, Enfu Huang, Junhao Huang, Changhao Jiang, Huicheng Jiang, Jiazhen Jiang, Shufan Jiang, Wenqing Jing, Jiahao Kuang, Bowen Lai, Bo Li, Qi Li, Qilong Li, Zhuoqun Li, Tianhao Liang, Jiaxiang Liu, Junzhang Liu, Shaofan Liu, Shuainan Liu, Tong Liu, Yi Liu, Ziyu Liu, Zhonghang Lu, Jianwen Luo, Xuan Luo, Yanyi Luo, Huijie Lv, Mingyu Ma, Houcheng Min, Hongjun Mo, Songhao Ni, Chengjun Pan, Qiyuan Peng, Xiaoxuan Peng, Wanying Ren, Runhui Ruan, Jifei Shan, Zixin Shang, Bing Shao, Zhuohui Sheng, Jiayang Shi, Qingyun Shi, Yang Shu, Aierpanjiang Simayi, Sirui Song, Yuxiao Song, Jiahao Sun, Zhe Sun, Wenzhe Tan, Guoxiang Wang, Hanchen Wang, Jie Wang, Pengbo Wang, Qing Wang, Rui Wang, Weihang Wang, Xiaotao Wang, Yuhui Wang, Zhekai Wang, Zihan Wang, Zile Wang, Jinke Wu, Liwei Wu, Xuansheng Wu, Yida Wu, Yihao Wu, Yinqi Wu, Yue Wu, Yuhan Wu, Yuwa Wu, Zhiheng Xi, Ying Xiao, Zhide Xie, Caijun Xu, Xingle Xu, Yichen Xu, Yongfeng Xu, Xiaolei Yang, Zhixiong Yang, Jiacheng Yao, Dingcheng Yi, Shihong Yi, Jinhui Yin, Peizhou Yu, Shan Yu, Hao Yuan, Junjie Yuan, Xiongyao Zha, Bo Zhang, Caixian Zhang, Kaicheng Zhang, Pengxiang Zhang, Qiuyinzhe Zhang, Wei Zhang, Xiaoqian Zhang, Xinsen Zhang, Jiyuan Zhao, Shuyu Zhao, Pujun Zheng, Zheyu Zheng, Xiaoxue Zhong, Peiheng Zhou, Xiaohao Zhou, Xinyu Zhou, Fangyi Zhu, Guanru Zhu, Yulun Zhu, Jiabao Zhuang, Pengfei Cao, Zhicheng Dou, Xianpei Han, Ben He, Guoxiu He, Xuanjing Huang, Tao Ji, Yu-Gang Jiang, Dahua Lin, Hongyu Lin, Kang Liu, Yaojie Lu, Le Sun, Ji-Rong Wen, Jun Zhao, Yutao Zhu, Qi Zhang, Bowen Zhou, et al. (106 additional authors not shown) Title: Sage S2.1 Flash Technical Report Arxiv: http://arxiv.org/abs/2611.21072v1 Abstract: We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S1.5 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench~2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench~II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.

    • Transcript
  • #2507
    Tuesday · 20 min

    SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

    🤗 Upvotes: 27 | cs.CR, cs.AI Authors: Woosang Lim, Yeseul Chang, Jaewoo Lee Title: SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection Arxiv: http://arxiv.org/abs/2611.07222v2 Abstract: Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money to an attacker. Many runtime defenses put a language model on the decision that lets an action through, so the decision depends on a model that may read the attacker's text and adds model calls to every step. Provenance defenses keep the model off the final check but need a model to plan or route each task first. Where an action goes can instead be read from the tools' typed returns: an email's sender or a payment's account arrives in a typed field, while injected instructions arrive as free text. SPILLWAY turns this observation into a deterministic floor with no per-task plan. The check admits a call when each target value that appears in tool output but not in the user's task was returned by a read-only tool in a typed field or is covered by a fixed delegation rule. A deterministic sanitizer removes instruction-like regions its fixed rules match before the model reads them and retains the removed spans as evidence, and a local judge may restore a refused call, never one whose target lies in the removed text. Across three backbones, and seven task suites on one of them, no standard templated injection redirects an action to an attacker's target under SPILLWAY, at the highest observed mean utility and composite scores (NRP, ERS) of the defenses we run under that attack. A forged chat template also produces a raw zero, and mean in-scope attack success under a released reinforcement-learning attacker is .005. SPILLWAY reaches this floor with no defense-triggered backbone re-run and almost no added model call. As personal AI agents act on users' email, files, and payments, SPILLWAY gives them an auditable refusal floor on where their actions go that keeps them useful and holds across backbones.

    • Transcript
  • #2506
    Tuesday · 24 min

    SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

    🤗 Upvotes: 27 | cs.SE, cs.AI Authors: Xinping Lei, Minghao Liu, Ruijie Zhu, Xiaohui Hu, Xingqiao Li, Ao Zhang, Wenhao Chai, Han Li, Tao Wang, Jingyuan Zhang, Enduo Zhao, Yunfeng Shi, Yiming Liang, Zetao Yang, Xingjian Wang, Yifan Yao, Xinkai Ma, Yingru Li, Tianhan Yang, Huan Zhou, Weiran Shi, Shen Yan, Jiaheng Liu, Stephen Huang, Eli Cheung, Weihao Xuan Title: SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations Arxiv: http://arxiv.org/abs/2611.20218v1 Abstract: A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests. We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements. Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

    • Transcript
  • #2505
    Friday · 22 min

    SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models

    🤗 Upvotes: 40 | cs.CL, cs.AI, cs.LG Authors: Lichen Li, Ziping Dong, Sicheng Feng, Qi Li, Xinchao Wang Title: SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Arxiv: http://arxiv.org/abs/2611.15777v1 Abstract: System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate performance on current benchmarks. Existing evaluations often provide limited insight into the breadth of model capabilities and the reliability of their decisions. We introduce SO-Arena, a benchmark characterizing the capability spectrum and decision reliability of System One models across 11 domains and five capability families. For the capability spectrum, SO-Arena offers evidence-grounded evaluation through reliable sources and manual verification of reference labels against model-visible inputs; fine-grained capability assessment through domain-specific difficulty criteria; and realistic interactive evaluation, where models iteratively execute actions in sandboxes. Reasoning-intensive tasks further enable system one-two comparison. Beyond accuracy, SO-Arena assesses decision reliability through two complementary measures: decision stability under controlled option-set changes and missing-answer recognition when no valid option is available. Evaluations across 21 models reveal that the benefits of scaling and additional reasoning vary substantially across domains. More importantly, strong overall performance does not necessarily imply reliable decision-making: the best-performing System One model ranks only seventh in reliability. Together, these findings highlight the need to characterize capability spectrum and decision reliability as complementary dimensions, providing a systematic view of the strengths and limitations of System One models.

    • Transcript
  • #2504
    Friday · 23 min

    BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model

    🤗 Upvotes: 37 | cs.CV Authors: Junyoung Seo, Jaewoo Seo, Seungryong Kim, Laura Leal-Taixé, Xiuming Zhang, Seung Wook Kim Title: BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model Arxiv: http://arxiv.org/abs/2611.14815v1 Abstract: Driving world models aim to simulate how a scene unfolds under different ego actions. This requires plausible motion of surrounding vehicles as well as precise ego-trajectory control. Learning vehicle motion from perspective video alone is challenging because motion is entangled with appearance and vehicles can be occluded. Prior work therefore conditions video generation on layouts that specify vehicle motion, providing control over surrounding vehicles but requiring their future trajectories as inputs. We introduce BirdDreams, an autoregressive driving world model that jointly generates perspective video and a schematic bird's-eye-view (BEV) video, making scene layout part of the predicted future. The BEV, rendered from scene annotations for training, depicts roads and vehicles as simple shapes at a fixed metric scale, providing a top-down view of their positions and motion with reduced occlusion between vehicles. Perspective video, by contrast, retains scene details that the BEV omits, such as traffic signals and object appearance. Joint attention between two video diffusion transformers, one per stream, lets each stream inform the other during generation. The predicted BEV also provides a geometric interface for ego control: we translate and rotate its latest frame along an input ego trajectory and use the resulting frames as a soft condition that shows how the scene would appear to move if only the ego vehicle moved. At inference, BirdDreams generates both videos from a single camera image without requiring an HD map or vehicle-state inputs. On PhysicalAI-AV and nuScenes, BirdDreams follows input ego trajectories more faithfully than prior driving world models and generates more plausible ego motion without ego-action conditioning. Human evaluation shows that BirdDreams outperforms a perspective-only baseline in generating realistic surrounding-vehicle behavior.

    • Transcript
  • #2503
    Friday · 20 min

    G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation

    🤗 Upvotes: 36 | cs.CV Authors: Xu Huang, Ye Huang, Xiaotong Li, Zhengrong Yue, Jialv Zou, Minhao Jing, Haodong Li, Wenhao Yan, Yaxin Luo, Duomin Wang, Daquan Zhou Title: G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Arxiv: http://arxiv.org/abs/2611.13004v1 Abstract: Discrete autoregressive models offer a scalable framework for image generation. However, they face a fundamental trade-off: long token sequences preserve representation quality but slow generation, while aggressive spatial compression reduces representation capacity. Based on product quantization, we show that, under a fixed nominal information budget, group size should scale quadratically with the per-axis spatial compression factor. Building on this principle, we propose GSTAR, a spatial--group co-scaling framework that enables \(32\times\) and even effective \(64\times\) compression while preserving strong reconstruction, understanding, and generation performance. Since larger groups introduce intra-group dependencies that must be modeled efficiently, we analyze their impact on inference latency and generation quality and introduce a semi-autoregressive decoder that combines parallel feature computation with lightweight causal modeling. With these designs, our highly compressed models perform competitively with leading models across five representative text-to-image benchmarks (GenEval, DPG-Bench, PRISM, LongText-Bench, and Qwen-Image-Bench). At \(1024\times1024\) resolution, our model delivers a \(20\times\) speedup over prior discrete autoregressive models, generating each image in 2.5 seconds on a single NVIDIA H200. Together, these results show that highly compressed discrete representations can enable high-quality autoregressive generation at low latency.

    • Transcript
Showing 1–20 of 360 episodes