跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 21:02 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 21:34 — 2026-11-22 21:34(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 21:02最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 25 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 21:00(北京时间)
版本更新 · v3arXiv:2602.07643

分割基础模型在结构与功能医学影像间的泛化能力如何?

How Well Do Segmentation Foundation Models Generalize Across Structural and Functional Medical Imaging?

Yichi Zhang, Le Xue, Feiyang Xiao, Wenbo Zhang, Gang Feng, Chenguang Zheng, Yuan Qi, Yuan Cheng 等 9 位作者

AI 速读 基于摘要

作者构建配对的PET/CT与PET/MRI全身多器官数据集UMD,并直接比较五个代表性3D分割基础模型在结构与功能影像上的开箱即用表现。

cs.CV

查看原文摘要

Segmentation foundation models offer reusable tools for universal medical-image segmentation, but their development and evaluation have largely centered on structural CT and MRI imaging. Functional imaging such as PET provides complementary metabolic information yet remains less studied and validated. Moreover, existing evaluations often involve different datasets and tasks, making modality-associated variation difficult to distinguish from differences in segmentation targets and data distributions. To enable a more direct comparison, we introduce UMD, a whole-body multi-organ dataset comprising 490 PET/CT and 464 PET/MRI examinations with 13 annotated organs (approximately 675,000 2D slices and 12,000 3D organ annotations). UMD evaluates structural and functional images separately on corresponding organs within the same examination, reducing variation in patient anatomy and target selection. We benchmark the out-of-the-box segmentation capabilities of five representative 3D foundation models on UMD. Overall, most evaluated models show limited PET segmentation performance, and some configurations also yield near-zero overlap on CT or MRI under the evaluated workflows. These findings highlight the need to assess tool applicability across different imaging conditions and identify opportunities for cross-modality generalization. UMD provides a paired data resource and evaluation setting for this investigation.

新论文 · v1arXiv:2611.24999

PsyWorld: Profile-Conditioned World Modeling for Human Behavior Prediction

Ziyuan Qin, Yang Qiao, Summer B. Frandsen, Michael T. Treadway, Liang Zhao

原文摘要

Understanding how stable psychometric traits and time-varying states jointly inform behavior is an important problem in computational behavioral science. Existing personalized agents commonly condition actions directly on a static profile, leaving realized state transitions unused as an explicit source of supervision. We introduce a profile-conditioned state world model that uses observed environment--behavior state transitions to learn transition-informed representations for behavioral prediction. During training, a posterior encoder quantizes realized transitions, while a prior predicts the resulting codes from the psychometric profile and pre-transition context. The prior code and predicted next state then condition macro-level behavior and simulator-grounded execution. Thus, the world model provides structured transition supervision instead of treating personality as a direct action descriptor. We evaluate the framework in VEET, a controlled behavioral simulator with human trajectories, and in AgentSociety as a structurally different synthetic environment. A participant-disjoint split of 240 training, 25 validation, and 48 test participants evaluates generalization to unseen people. On VEET, the model reaches 0.904 Top-1 accuracy (95\% CI: [0.895, 0.913]) and 0.0033 Macro KL. Ablations associate continuous next-state modeling with most of the Top-1 gain, while discrete codes and prior alignment mainly improve Top-3 and distributional alignment. These results establish transition-informed world-model supervision as useful for subject-generalized behavior prediction, without implying causal psychological mechanisms or calibrated long-horizon state dynamics.

cs.LG

新论文 · v1arXiv:2611.24006

MARS Technical Report

Tong Liu, Chaoqun Hou, Longxiang Xiong, Junhong Lou, Jiaqi Zheng, Qixin Li, Zixin Zhao, Yong Duan 等 17 位作者

原文摘要

Modern industrial recommender systems use multi-stage cascades--retrieval, pre-ranking, ranking, and re-ranking--to narrow millions of candidates to a personalized list. While each stage deploys sophisticated models, pipeline-level decisions on channel activation, quotas, model selection, and score fusion remain engineer-tuned and user-agnostic within each scenario. This report presents MARS (Multi-stage Agentic Recommendation System), extending personalization from individual-stage predictions to full pipeline orchestration. A near-line agent built on fine-tuned Qwen3-0.6B generates per-user configurations--a seven-dimensional action covering pipeline mode, retrieval quotas, model selection, fusion weights, and reranker settings--from a constrained action space. Configurations are validated, cached, and consumed asynchronously; the cascade never waits for LLM inference. Schema checks, fallbacks, and a kill switch ensure serving safety. The policy is trained in three stages: Confidence-aware SFT distills schema-valid generation from a teacher model; Format-Anchored Preference Optimization (FAPO) learns action preferences via ActionMask with posterior weighting; Group Relative Policy Optimization (GRPO) refines the policy through Sandbox replay with a frozen reward model, without exposing exploratory actions to live traffic. Two-week A/B tests across five Taobao scenarios with over ten million daily users show positive gains on all key metrics. The largest reach +5.22% V2P and +7.34% GMV, with positive CTR lifts on both click surfaces. About 20% of requests use a lightweight Minimal mode, and deployment shows 12 ms lower mean serving latency versus production.

cs.IR

版本更新 · v2arXiv:2606.12563

Arbor: How Search Policy Shapes Agent Behavior in System Optimization

Neha Prakriya, Chaojun Hou, Zheng Gong, Huasha Zhao, Yanyuan Qin, Chris Cai, Xi Zhao, Zhenyu Gu 等 9 位作者

原文摘要

Achieving peak performance on modern accelerators requires coordinated optimization across kernels, operator fusion, KV-cache management, quantization, scheduling, and communication overlap, a process that demands weeks of expert effort per model and hardware platform. We present Arbor, a system that gives autonomous agents an explicit optimization tree to reason over, backtrack through, and deepen with experience, with pluggable search policies, scored bandit traversal, parallel agent swarms, and depth-first sweep, sharing a common harness of containerized isolation, automatic rollback, and end-to-end validation. Arbor generalizes across domains: +40% to +193% on six production inference models across two GPU generations, +42.8% on LLM training, and +41% on recommendation training, where agents autonomously wrote kernel-level and framework-level optimizations spanning thousands of lines of code. In controlled ablations where every search policy receives the same agent, tree, and tools, we find that search structure shapes both the magnitude and the nature of the optimizations. The bandit achieves +30.1% through targeted framework fixes, the sweep +26.4% through deep kernel rewrites, and the swarm +33.4% by compounding independent changes. An agent-driven loop that receives the same harness, tools, and information, but selects its own targets reaches +14%, writing 4x more code per percentage point of improvement than Arbor's structured search policies. We additionally introduce an evaluation framework for autonomous loop-based agents spanning efficiency, grounding, robustness, and depth, designed to characterize agent search behavior across long-running optimization campaigns.

cs.AI

新论文 · v1arXiv:2611.22301

MCTS Is Counting the Wrong Thing: Learning Exploration Counts for LLM Reasoning

Xuan Zhang, Zhijian Zhou, Zicheng Hu, Yan Feng, Hongyan Hao, Yuan Qi, Chao Qu

原文摘要

Monte Carlo tree search (MCTS) has powered landmark successes in reinforcement learning, yet its gains in LLM reasoning can remain modest despite substantial search effort. We identify an overlooked bottleneck: what MCTS counts. Standard UCT assigns independent visit counts to textual branches, allowing different formulations of the same reasoning strategy to repeatedly receive exploration bonuses. Our theoretical analysis shows that this count fragmentation can impair exploration efficiency, as quantified by increased cumulative regret. To address this problem, we introduce Learned Pseudo-Count MCTS (LPC-MCTS), which changes only the exploration statistic in UCT. A lightweight Coin-Flipping Network head on the policy's hidden representations estimates representation coverage, enabling related branches to share exploration evidence. Across 5 mathematical-reasoning and 7 search benchmarks, LPC-MCTS consistently outperforms strong MCTS baselines. Holding each LPC-MCTS-trained policy fixed, replacing standard MCTS counts at inference improves average mean@16 accuracy across 5 mathematical benchmarks by 3.79 percentage points on Qwen2.5-7B and 2.71 points on Qwen3-4B. Applying LPC-MCTS during both training and inference yields gains of 4.96 and 4.37 points over standard MCTS, respectively. Together, our theory and experiments show that changing what MCTS counts can substantially improve its exploration efficiency and reasoning performance.

cs.AI

新论文 · v1arXiv:2611.21469

变分正确的物理信息算子学习用于非线性偏微分方程

Variationally correct physics-informed operator learning for nonlinear partial differential equations

Yuan Qiu, Wolfgang Dahmen, Peng Chen

AI 速读 基于摘要

作者提出并验证了一种基于一阶系统最小二乘残差的物理信息算子学习方法,用于非线性偏微分方程,其损失在理论上等价于PDE合规范数下的误差,并在数值上优于网格基线。

math.NA · cs.LG

查看原文摘要

Physics-informed operator learning trains neural operators on the residual of a parametric partial differential equation (PDE) instead of labeled solution data, but its reliability depends on a variationally correct residual: one that is equivalent to the error in a norm dictated by the equation, the PDE-compliant norm. For nonlinear equations written as first-order systems, we prove that the first-order system least-squares residual is equivalent to the error in this norm near a solution branch if the linearized residual is stable and the residual derivative is Lipschitz continuous, possibly in a norm stronger than the error norm. We verify these conditions for monotone reaction, solution- and gradient-dependent diffusion, and compressible Neo-Hookean hyperelasticity. The stability mechanisms vary across these classes, as do the regions where the equivalence holds, from arbitrary bounded sets to a neighborhood of the branch. In a conforming finite element space, we show that the loss excess of a state near the finite element solution is equivalent to its squared distance from that solution. We use this loss to train a reduced basis neural operator with values in this space, with solution snapshots needed only for the basis and the loss and its symbolically derived gradient assembled by the finite element library. At inference, this loss estimates the error. Numerically, the square root of the loss excess tracks the error within factors comparable to those of the linear case, and the operator achieves higher accuracy in the PDE-compliant norm than grid-based baselines evaluated in the same finite element space.

版本更新 · v2arXiv:2407.06168

TARGO and TARGO-Net: Benchmarking Target-driven Object Grasping under Occlusions

Yan Xia, Ran Ding, Ziyuan Qin, Guanqi Zhan, Kaichen Zhou, Long Yang, Hao Dong, Daniel Cremers

原文摘要

Predicting 6-DoF grasp poses from a single RGB-D frame has recently achieved impressive accuracy, yet performance can degrade significantly when the target object is heavily occluded by clutter. In this paper, we establish TARGO, the first benchmark dataset for TARget-driven Grasping under Occlusions, and introduce TARGO-Net, a grasp prediction model designed for visual occlusion. Our main contributions are fourfold: 1) We identify the visual occlusion challenge in single-view RGB-D 6-DoF grasping and show that current state-of-the-art models still suffer under severe occlusion. 2) We propose the TARGO dataset, which supports training and testing 6-DoF grasp models across different visual occlusion levels and enables robustness evaluation in real-world scenarios. 3) We devise TARGO-Net, a transformer-based grasping model with a target completion module and target-scene cross-attention, which achieves the most robust performance across all visual occlusion levels. 4) We show that target completion, number of occluders, and target minimum dimension also relate to grasp success in addition to visual occlusion.

cs.RO · cs.CV

新论文 · v1arXiv:2611.17621

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

AI Training Platform Team, Bingwei Zhang, Jing Li, Amir Abdullin, Sihang Chen, Xin Chen, Liangjun Feng, Yingmeng Gao 等 27 位作者

原文摘要

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.

cs.AI · cs.DC · cs.LG

版本更新 · v3arXiv:2611.08577

美团机器人-0:面向桌面操作视觉-语言-动作基础模型

Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation

Meituan Robotics Team, Caicheng Wang, Chen Zhao, Chengpeng Jin, Duo Xu, Fengjiao Chen, Guanglu Wan, Heqing Yang 等 38 位作者

AI 速读 基于摘要

MR0 是一个面向固定底座桌面操作的视觉-语言-动作基础模型与具身智能体系统,通过三阶段训练和 Rollback 数据机制实现跨本体控制与任务恢复。

cs.RO · cs.CV

查看原文摘要

We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than $π_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.

版本更新 · v3arXiv:2610.15221

HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems

Zhaoyuan Qiu, Sachith Seneviratne, Yu Xia, Saman Halgamuge

原文摘要

AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation models frozen. Existing studies focus on single agents, leaving joint harness evolution in multi-agent systems (MAS) underexplored. A single global optimizer faces growing context and workload as the system scales, while access restrictions may prevent sharing agent internals or system-wide feedback. We propose HarnessNet, a framework for hierarchical harness evolution in MAS. Its basic unit, Agentron, comprises an evolvable forward harness, a foundation model, and a local optimizer that can observe and modify only that harness. Agentrons form a layered graph through which environment feedback propagates backward, with upstream optimizers receiving node-specific feedback from the downstream layer. This decomposes joint harness evolution into smaller, coordinated tasks with separate contexts, reducing individual optimizers' context and workload while keeping access local. Optimizers need not access all agent trajectories or raw environment feedback. Experiments on AgentBench with multiple foundation models demonstrate the feasibility of training HarnessNet. Compared with a single global optimizer, HarnessNet achieves comparable performance gains while respecting local privacy and requiring fewer tokens and less time per optimizer call. A migration study shows that the evolved harnesses remain jointly effective after replacing the foundation models, suggesting transferability across models.

cs.AI

版本更新 · v2arXiv:2610.08446

AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly

Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu

原文摘要

Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58\% to 62.80\% and Tree Exact Match from 28.24\% to 53.92\% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves judge-accepted operations from 0 to 5.3\% and reduces mean Chamfer distance from 5.4111 to 1.7744. However, visually plausible candidate poses may still suffer from collision, floating, mirror-orientation errors, incomplete seating, and wrong-side attachment. These results show that AssemState improves operation-structure recovery and selected local pose metrics, while MLLMs remain limited for spatial relationship reasoning.

cs.AI

版本更新 · v5arXiv:2505.23086

Equivariant Spherical Transformer for Efficient Molecular Modeling

Junyi An, Xinyu Lu, Yunfei Shi, Peijia Lin, Licheng Xu, Qianwei Tang, Chao Qu, Fenglei Cao 等 9 位作者

原文摘要

Equivariant Graph Neural Networks (GNNs) have significantly advanced the modeling of 3D molecular structure by leveraging group representations. However, message passing built only from exactly equivariant operations can have restricted practical expressiveness at a fixed representation degree. We introduce the Equivariant Spherical Transformer (EST), a plug-and-play module that applies Transformer attention to spherical spatial representations obtained from group representations. EST explicitly mixes information across sampled orientations, unlike prior orientation-wise spherical operations, while retaining a strong approximate equivariant inductive bias through near-uniform spherical sampling. As demonstrated by our experiments on challenging benchmarks like OC20, MPtrj and QM9, EST-based models achieve state-of-the-art performance. For the complex molecular systems within OC20, small models empowered by EST can outperform some larger models and those using additional data. We characterize the ideal closed-domain condition under which the continuous operation is exactly equivariant and empirically quantify the finite-sampling accuracy--equivariance--memory trade-off used in practice.

cs.LG · cs.AI

版本更新 · v2arXiv:2509.18937

Lang2Morph: Language-Driven Morphological Design of Robotic Hands

Yanyuan Qiao, Kieran Gilday, Yutong Xie, Josie Hughes

原文摘要

Designing task-specific robotic hands requires translating diverse task requirements into morphologies that are both functional and manufacturable. Existing parametric and optimization-based approaches provide systematic design tools, but often rely on expert-defined objectives, manual tuning, or simulation-based search. Large language models (LLMs), with broad semantic knowledge and reasoning capabilities, offer a promising way to interpret task requirements directly from natural language. We present Lang2Morph, an LLM-driven framework that maps natural-language task descriptions to fabricable robotic hand morphologies within the Open Parametric Hand (OPH) design space. Lang2Morph combines task reasoning, structured morphology generation, geometric constraints, and feedback-guided selection to produce task-conditioned hand designs. Morphology-level analyses demonstrate high design feasibility and task-dependent structural variation, while real-world experiments with three fabricated hands reveal distinct functional characteristics across manipulation tasks. These results highlight the potential of LLMs as practical interfaces for task-driven robotic hand design.

cs.RO

版本更新 · v2arXiv:2603.24500

Project and Generate: Divergence-Free Neural Operators for Incompressible Flows

Xigui Li, Hongwei Zhang, Ruoxi Jiang, Deshu Chen, Chensen Lin, Limei Han, Yuan Qi, Xin Guo 等 9 位作者

原文摘要

Learning-based models for fluid dynamics often operate in unconstrained function spaces, leading to physically inadmissible, unstable simulations. Penalty-based methods can reduce constraint violations but do not guarantee exact incompressibility. In this work, we introduce a unified framework that enforces the incompressible continuity equation as a hard, intrinsic constraint for both deterministic and generative modeling. We integrate a differentiable spectral Leray projection into neural operators to enforce incompressibility. For flow matching, we construct a divergence-free Gaussian reference measure via a curl-based pushforward, so that the reference samples, interpolation paths, and velocity targets are compatible with the projected dynamics. Experiments on 2D Navier-Stokes equations demonstrate exact incompressibility up to discretization error and substantially improved stability and physical consistency.

cs.LG · physics.flu-dyn

版本更新 · v2arXiv:2607.13455

反向以进阶:从反向简单任务中进行遥操作成本有效的高难度策略学习

Reverse to Advance: Teleoperation-Cost Effective Hard Policy Learning from Reversed Easy Tasks

Qiyuan Qiao, Ge Yuan, Can Wang, Dong Xu

AI 速读 基于摘要

提出一种通过时间反转简单任务来自动生成并精炼监督数据、从而低成本学习高难度操作策略的框架。

cs.RO

查看原文摘要

High-quality teleoperation datasets are costly to collect, particularly for hard tasks. We observe that many tasks exhibit directional asymmetry: completing the forward hard task is difficult, whereas reversing it by relaxing or disrupting the environment is comparatively easy. This suggests that reversed easy-task trajectories can serve as a scalable supervision signal for the hard task, reducing the cost of manual demonstration collection. However, reversed data can be noisy, and directly training on it may yield suboptimal policies. To enable largely automated acquisition and effective use of reversed data, we propose a teleoperation-cost effective framework for hard policy learning via temporal reversal of easy tasks, consisting of three key components: a closed-loop data collection pipeline that alternates between hard-task and easy-task policies to autonomously reset the environment and generate diverse trajectories; a hierarchical data refinement pipeline that temporally inverts easy-task rollouts and filters low-quality motion using kinematic priors and a critic-guided advantage filter; and an iterative policy learning method that trains the hard-task policy using both initial reversed easy-task demonstrations and the filtered reversed data in a continuous online learning loop. By combining automated collection, hierarchical refinement, and iterative learning, our method enables scalable, reliable training of complex, high-precision manipulation tasks. Across two simulated benchmarks and real-robot experiments, we demonstrate that our method improves hard-task success rates with higher data efficiency and more stable training compared to reversal-based and reinforcement-learning baselines, without requiring extensive hard-task teleoperation.

新论文 · v1arXiv:2611.06977

BlockLock: Reproducible LLM Inference with Fixed Batch Geometry

Xiuyuan Qi, Pedro Reviriego, Javier Conde, Shanshan Liu

原文摘要

Reproducible LLM inference requires that a request produces the same output regardless of the other requests in the batch. Existing solutions pay for this in different ways: batch-invariant kernels constrain every operator, and isolating prefill with fixed-shape decode ({our CoRun-style baseline}) gives up shared prefill compute and pads decode. We present BlockLock, which keeps shared batched prefill and pins only the numerical path of the protected request: it fixes the geometry that the request sees, with {two modes: BlockLock-Rows uses fixed-width rows and retains batched decode of all requests; BlockLock-Pack uses terminal-anchored packing with an isolated dummy segment, then extracts the protected request's KV state for target-only decode. Under a stated per-deployment contract, both modes preserve the target's output bitwise when its companions change.} Across five {dense} models (Qwen3-8B/14B, Llama-3.1-8B-Instruct, and Gemma-3-4B/12B-IT) and three single-GPU deployments (NVIDIA A6000, A100, and H100), we evaluate our approach on both tinyBenchmarks and BFCL{; we also include initial tensor-parallel experiments on two NVIDIA A6000 GPUs. Both modes preserve target sequences and Top20-logit bits in the reported tests.} At equal delivered work, {BlockLock-Rows} reduces latency by 53.5--55.0\% and improves throughput by 115.2--122.2\% relative to vLLM Batch-Invariant; compared with batch-invariant kernels, it needs no custom kernel implementations and constrains only the protected requests.

cs.AI · cs.CL

新论文 · v1arXiv:2611.05751

Scheduling Data to Compute: Hierarchical Data Pipelining for LLM Training on AMD GPUs

Gengyu Rao, Ghadeer Ahmed H Alabandi, Su Ann Chong, Thomas Huber, Kailash Gogineni, Subhajit Dutta Chowdhury, Saleel Kudchadker, Suchita Pati 等 31 位作者

原文摘要

Large language models (LLM) have been the key focus of recent machine learning breakthroughs. As the model size grows exponentially, the computation needed for training is astronomical. A GPU can do a huge amount of arithmetic. However, the data its compute units need is not always available when they are ready. This data may still be in slow memory or on another GPU. While the chip waits, expensive compute sits idle, and at scale even a small drop in utilization translates into substantial cost. In this paper, we treat this waiting time as the primary bottleneck. We focus on hardware features designed for explicit data movement. These features load data from off-chip memory onto the chip, rearrange it into the layout the computation requires as it is loaded, and transfer it between GPUs. By orchestrating them, we keep a steady pipeline of data flowing to the compute units so that they remain busy. We present kernel and framework implementations that address this bottleneck using three key data-movement instructions and hardware features. The Tensor Data Mover (TDM) moves tensor data from high-bandwidth memory (HBM) into on-chip memory. Transpose-load instructions transpose tensor data into the layout that LLM computations require as it is loaded on-chip. Finally, System DMA (SDMA) and Remote DMA (RDMA) move data between GPUs over the scale-up and scale-out networks, respectively. Our results show that TDM and transpose-load provide on average 1.88x and 1.19x speedup at the kernel level, respectively. The SDMA and RDMA lead to on average 1.16x and 1.33x speedup for computation overlapped with communication. This is the first AMD LLM training system to utilize all the GPU data pipelining features. Our implementation has been integrated into open source framework and library for AMD GPUs. https://github.com/AMD-AGI/Primus-Turbo https://github.com/AMD-AGI/Primus

cs.AR · cs.AI

新论文 · v1arXiv:2611.04493

Physical Diffusion Policy via MPM-Guided 3D Gaussian Simulation

Can Wang, Qiyuan Qiao, Lei Liu, Ge Yuan, Xinhui Liu, Dong Xu

原文摘要

Learning robust manipulation policies for diverse everyday objects remains challenging because objects with different materials exhibit distinct deformation and contact dynamics. While diffusion policies provide a powerful framework for modeling multimodal manipulation behaviors, they typically lack explicit physical reasoning and may produce averaged actions when facing heterogeneous objects. We present a physics-aware diffusion policy that augments visual imitation learning with object physical understanding. Our framework recovers material properties from visual demonstrations by coupling 3D Gaussian Splatting with differentiable Material Point Method simulation, where video guidance and particle-level constraints enable accurate physical parameter estimation. The estimated physics conditions are further integrated into a material-aware Mixture-of-Experts diffusion policy, allowing adaptive behavior generation across different physical regimes. For practical deployment, we introduce a physics memory bank that provides efficient physical retrieval without requiring online simulation optimization. Experiments on a wide range of simulated and real-world objects demonstrate improved manipulation success and generalization over existing diffusion-based approaches. These results show that incorporating physical knowledge is critical for scalable robot manipulation in diverse environments.

cs.RO

版本更新 · v2arXiv:2606.28447

SemFlowRAG: Directed Semantic Flow from Abstraction to Evidence for Complex Reasoning

Houyuan Qin, Rong Wu, Qinyuan Qin, Botian Shi, Jingjing Qu, Yang Sun, Pinlong Cai

原文摘要

Retrieval-Augmented Generation (RAG) enhanced by Knowledge Graphs has shown promise in complex multi-hop reasoning tasks. However, existing graph-based retrieval methods typically rely on flat, undirected topologies. During the retrieval process, the probability flow often gets trapped in high-degree abstract concept nodes which we define as ``probability black holes'', leading to semantic drift and noise accumulation. To address this, we propose SemFlowRAG, a framework that reconstructs the flat retrieval space into a corpus-adaptive semantic gradient graph. This data-driven self-organization enables a hierarchical structure to emerge naturally from the data distribution, capturing the intrinsic semantic granularity of the corpus to suppress structural noise. By quantifying the semantic abstractness of entities through the embedding variance of their associated passages, we transform static undirected edges into directed semantic constraints. Furthermore, we design an abstractness-guided directed PageRank algorithm that forces the retrieval trajectory to follow a ``high-to-low semantic abstractness'' gradient. This mechanism ensures layer-by-layer evidence convergence, smoothly guiding the retrieval process from abstract concepts to specific document evidence. Extensive experiments on complex QA datasets demonstrate that SemFlowRAG effectively mitigates the ``probability black holes'' issue, outperforming existing baselines in both retrieval and downstream reasoning performance.

cs.IR · cs.AI

新论文 · v1arXiv:2611.01966

Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected?

Yuntong Hu, Hongji Pu, Zimo Li, Ruomeng Li, Xiaotong Liu, Ziyuan Qin, Qiyue Li, Liang Zhao

原文摘要

Coding agents can now rewrite repository-scale codebases while preserving tested behavior, creating a new challenge for plagiarism detection, license auditing, and software provenance. We ask whether such rewrites can still be traced to their source. Existing clone benchmarks emphasize fragments and bounded edits, while repository-transformation benchmarks evaluate functional correctness rather than provenance. Moreover, ranking the most similar source does not establish derivation when independent implementations can be similarly close. We define repository-level agentic code laundering and introduce Launder-Bench, to our knowledge the first repository-level benchmark for provenance under agentic rewriting, constructed from 282 real-world repositories. A source-hidden reconstruction protocol decomposes source behavior, reconstructs modules and repository structure, and retains rewrites only after execution-based verification. We evaluate the same provenance problem in two complementary settings: Launder-Bench-Pair contains 1,128 pairwise instances asking whether two repositories share provenance, while Launder-Bench-Attr contains 229 source-attribution instances asking which candidate is the source, with abstention when evidence is insufficient. Measured same-domain independent repositories establish how much similarity can arise without shared provenance and provide detector-specific reference bands. Existing methods remain far from saturating Launder-Bench: the strongest static method reaches only 0.66 AUROC on pairwise detection, while repository encoders rank the true source first on up to 22% of attribution queries but earn calibrated attribution credit on only 1-2%. These results reveal a systematic gap between relative code similarity and source-specific provenance evidence, providing a reproducible target for provenance detection under agentic rewriting.

cs.SE · cs.AI

新论文 · v1arXiv:2610.39415

Accuracy is not compatibility: two Evo 2 checkpoints hinge on one FP8 matrix multiplication

Xun Ding, Ziyuan Qin

原文摘要

FP8 formats specify how values are stored, not how products are summed; this gap can break checkpoints. Evo 2, a DNA language model, documents a Hopper FP8 requirement for its 1B and 40B checkpoints. On two Blackwell (sm_120) GPUs both fail the developers' forward test (the 7B passes); on an RTX 5070 Ti the 40B's next-base accuracy is 25.7%, near guessing. Greater accuracy breaks them, as BioNeMo saw for the 40B on Hopper: natively, 99.996% of one projection's outputs are correctly rounded (H100: about 30%), and fp32 accumulation of the same operands fails. Our H100 FP8 GEMM emulator, mmaemu (bit-exact on captured 1B projections), localises the dependence to the 1B's first projection (of 21), where exact sums fail but pass when shrunk by the H100's 1.4% (measured in-sample), not 2.1%. The 40B fails with only its first projection native. Emulating only that projection, weights unchanged, raises 40B BRCA1 variant-classification AUROC from 0.434 to 0.869 (H100: 0.868) on the RTX 5070 Ti, despite a narrow forward-test miss, and 0.481 to 0.867 on an RTX PRO 6000. We tested one model family but not training origin; releases should specify reference arithmetic.

cs.LG

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.402ACL Anthology · ACL 2026

QBridge: Bridging Natural Language and SQL via Gold Query Rewriting with Agentic Refinement

Zhensheng Luo Zhejiang University, Sai Wu Zhejiang University, Yuan Qiu, Chang Yao Zhejiang University, Gang Chen College of Computer Science and Technology, Zhejiang University, Xiu Tang Zhejiang University

原文摘要

Natural language to SQL (NL2SQL) provides an intuitive interface for querying structured data, yet real user questions are often noisy, ambiguous, and weakly grounded to database semantics.As a result, token-level schema linking and single-pass SQL decoding can be brittle: small misunderstandings in language or schema grounding may propagate into incorrect generation.We present QBridge, an agentic, feedback-driven NL2SQL framework based on a Refined Gold Query Paradigm, which bridges natural language and SQL via Gold Query—a structured, SQL-aligned intermediate representation.A core insight of QBridge is Distilled Back-Translation (DBT) for SL-independent rewriting.DBT converts SQL-grounded supervision into execution-verified Gold-Query-style rewrites from a teacher model, and distills a lightweight, plug-and-play rewriter that generates schema-aware rewrites without requiring explicit schema linking at inference.QBridge then (i) verifies and conservatively refines the rewrite into a high-fidelity Refined Gold Query, and (ii) refines the generated SQL with dual feedback from execution validity and semantic consistency, enabling interpretable self-correction while remaining compatible with diverse SQL backbones.Extensive experiments on Spider, BIRD, and three robustness variants demonstrate that QBridge consistently improves zero-shot NL2SQL, outperforming strong prompting and agentic baselines while showing strong robustness and generalization. Code and data are available at https://github.com/WannaBSteve/QBridge.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.441ACL Anthology · ACL 2026

IEvoAgent: Evolving Conversational Agent based on User Implicit Feedback

Yichen Cai, Jiayang Li, Junyuan Qiu Zhejiang University, Jingya Guo Alibaba Group and University of Hong Kong, Weitao You, Changyuan Yang, Lingyun Sun Zhejiang University, Pei Chen

原文摘要

Current conversational agents often follow static learning paradigms and miss the implicit, evolving feedback embedded in users’ follow-up behaviors. We propose IEvoAgent, an evolving conversational agent framework that leverages the structured dependency between agent responses and user reactions. We construct an annotated dataset from LMSYS-Chat-1M and WildChat and find consistent response-conditioned feedback patterns. Based on this finding, IEvoAgent uses a conditional feedback distribution matrix to estimate expected feedback rewards, combining offline KTO alignment with an inference-time prompt-evolution mechanism driven by a dynamic matrix. Experiments on MT-Bench-101, WildBench, and FB-Bench show improvements over open-source baselines, indicating that mining implicit feedback supports better multi-turn alignment under evolving user preferences. Our code and dataset are available at https://github.com/Hualeez/IEvoAgent.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.74ACL Anthology · ACL 2026

Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning

Shuyao Xu University of Virginia and National University of Singapore, Cheng Peng, Jiangxuan Long University of Hong Kong, Weidi Xu Infly Technology, Wei Chu Inf Tech, Yuan Qi Fudan University

原文摘要

Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models. However, standard practices discard incorrect reasoning traces—valuable, yet underutilized data. This paper addresses the critical question: How can both positive and negative distilled reasoning traces be effectively leveraged to maximize LLM reasoning performance in an offline setting? We employ a two-stage training recipe: first, Supervised Fine-Tuning (SFT) on positive traces, followed by a refinement stage using both positive and negative traces. We find that a simple REINFORCE-style objective, which we term the Reinforcement Distillation (REDI) objective, outperforms established preference optimization methods like DPO and SimPO in this distillation context. Our empirical evaluations demonstrate the effectiveness of this approach. Notably, our Qwen-REDI-1.5B model, trained on just 131k traces from the open Open-R1 dataset, achieves an 83.1% score on MATH-500. Its performance matches that of DeepSeek-R1-Distill-Qwen-1.5B, a model trained on 800k proprietary data. This result showcases the remarkable data efficiency of utilizing previously discarded negative traces.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

版本更新 · v5arXiv:2403.05530Google Research

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent 等 1137 位作者

原文摘要

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

cs.CL · cs.AI