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
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 08:22 — 2026-11-16 08:22(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:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 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 116 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.17167

行动者、评判者还是教师?理解长程智能体中的决策模型

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

Haochen Liu, Qianhao Zhu, Zixuan Wang, Dingming Li, Tongbo Chen, Peng Qiu, Yingqi Qu, Weiming Lu 等 10 位作者

AI 速读 基于摘要

论文比较决策模型作为行动者、评判者与教师三种角色,提出表现差的行动者仍可能通过事后评判成为好教师。

cs.AI · cs.CL

查看原文摘要

Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studied them mainly as actors, judging their usefulness by how well they act. We ask whether a decision model that acts poorly can still teach well. We compare three decision models and three general LLMs as actors and judges on ALFWorld, and use JEV as a teacher on ALFWorld and WebShop. As actors, all six models are pulled away from a subgoal that must come first by an easier one. As judges that see the whole trajectory, the same models credit the steps toward that subgoal, and asking whether each action helped, rather than whether the task will succeed, separates useful from useless actions. As a teacher, JEV raises a Qwen2.5-1.5B policy over GRPO from 72.8% to 82.9% success on ALFWorld and from 56.8% to 71.4% on WebShop. These results suggest that a poor actor can still teach well, because judging an action after the episode ends reveals the consequences that acting must anticipate. Code is available at https://github.com/ZJU-REAL/decision-agents.

新论文 · v1arXiv:2611.16579

ActWorld-JEPA: Action-Conditioned JEPA World Models Meet Latent Planning for End-to-End Autonomous Driving

Ziying Song, Shengkai Zhang, Caiyan Jia, Lei Yang, Lin Liu, Yuchen Liu, Ziyang Liu, Zirui Li 等 13 位作者

原文摘要

Joint-Embedding Predictive Architectures (JEPAs) enable future prediction in latent space without pixel reconstruction. However, latent predictive consistency alone does not establish the relative driving quality of candidate plans. We present ActWorld-JEPA, a joint-embedding formulation for candidate-based driving. Where Plan-Conditioned JEPA (PC-JEPA) uses global and step-wise trajectory intentions to guide recurrent latent prediction, then combines the predicted future with the current scene through gated cross-attention; Relational Residual Reranking ($R^3$) models agreement and discrepancy between plan and future representations under planning supervision, yielding bounded, gated residual corrections to the base planning scores. This formulation connects latent prediction to candidate selection using only observed context and proposed trajectories at inference. Benchmark-specific implementations report 94.1 PDMS on NAVSIM v1 navtest, with the final selector calibrated using aggregate NAVTEST feedback, and 91.6 and 42.7 EPDMS on NAVSIM v2 navtest and navhard, respectively. The nuScenes evaluation reports a mean $L_2$ error of 1.20 m and a predicted collision rate of 0.76% over 1--6 s. This work provides an effective path from JEPA's predictive representations to driving decisions informed by anticipated consequences.

cs.CV

新论文 · v1arXiv:2611.16467

SS-HSDP: Efficient and Flexible Sharded Data Parallelism via Runtime-Update Decoupling

Chendong Xiang, Pengle Zhang, Jinliang Li, Zichen Liang, Jintao Zhang, Fan Bao, Jun Zhu, Jianfei Chen

原文摘要

Sharded data parallelism enables memory-efficient training of large models. While efficient training kernels favor packed, kernel-specific data layouts, optimizers may require variant data structures as optimization units. Existing sharded data-parallel frameworks couple these two choices, limiting runtime efficiency and optimization flexibility. To address this, we present \textbf{\our}, a training framework that separates runtime parameters from update parameters, allowing computation layouts and optimization units to be organized independently. Through shared data views and hierarchical sharding, \our supports this separation while avoiding redundant data movement. This design supports a broad range of optimizers, including matrix-based methods such as Muon, and performance optimizations such as fully zero-copy execution. Experiments on video and language model workloads with MXFP8 training show that \our achieves higher Model FLOPs Utilization (MFU) than FSDP2, veScale-FSDP, and Megatron-FSDP. At 128 GPUs, MFU improves by up to 21.7\% over the fastest evaluated baseline, with comparable or lower peak memory usage.

cs.DC

版本更新 · v2arXiv:2611.12304

Evolving Infra: Agent-Adaptive LLM Serving at Scale

Hao Kang, Weili Xu, Ziyang Li, Zheng Du, Hanchen Li, Tian Xia, Song Bian, Tushar Krishna 等 11 位作者

原文摘要

Agentic workloads are a major source of LLM inference demand. Existing prefill--decode (PD) disaggregated serving systems offer limited flexibility for runtime adaptation of compute allocation and KV cache management, and rely on coarse signals that only partly capture the diverse and dynamic agent workload. These limitations lead to load imbalance between prefill and decode nodes and eviction of KV caches that agents will reuse. We present Evolving Infra, an agent-adaptive serving framework that adapts compute allocation to agent workloads and KV cache management to agent context management at runtime. We decouple compute allocation from key--value (KV) cache management, allowing nodes to switch efficiently between prefill and decode. Building on this design, an online planner matches the PD split to workload composition, while an agent-aware distributed KV manager guides cache eviction and transfer with signals from agent context management. Across coding, math, and computer-use tasks with GLM-5.2 and Kimi K2.6 on up to 256 GB300 GPUs, Evolving Infra reduces mean end-to-end request latency and P95 TTFT by up to 4.1x and 14x over Dynamo, NVIDIA's production framework. We open-source the system implementation of Evolving Infra at https://github.com/mit-han-lab/EvolvingInfra.

cs.DC

新论文 · v1arXiv:2611.16205

QVS-LIVO RiskMap: Health- and Information-Aware View Selection for Multi-Camera LIVO and Off-Road Risk Mapping

Zihan Pan, Jinghan Wang, Hang Li, Feng Cheng, Tianchen Liu, Gaoliang Peng

原文摘要

Multi-camera observations in off-road environments vary significantly in reliability, posing challenges when complementing degraded geometric constraints. Motivated by this, we propose Quality-aware View Selection Lidar-Vision Odometry Risk Mapping (QVS-LIVO RiskMap), which decouples visual processing for state estimation from that for semantic mapping. The front end evaluates camera observations through read-only pretracking on a shared lidar-inertial posterior, combining observation health with geometric complementarity. Channel health memory and switching hysteresis govern selection of at most one eligible view for direct photometric correction. The posterior is retained when no view is eligible or the correction fails acceptance. The mapping back end integrates semantic observations from all available views in a shared world grid. Vehicle-scale geometry constrains semantic risk corrections, while spatial and temporal evidence supports risk confirmation. The system also produces a local bird's-eye-view (BEV) risk map and a global 2.5D semantic-terrain risk map with obstacle instance voxels. On two field sequences, QVS-LIVO achieved horizontal root mean square errors of 0.910 m and 1.664 m. It reduced error by 43.3% relative to FAST-LIO2 on the degraded long-route sequence. Across 12 controlled camera-fault configurations involving dropout, black frames and 60 ms timestamp shifts, it maintained complete trajectories with errors of 1.54-2.23 m. When deployed onboard an NVIDIA Jetson AGX Orin, the system generates local and global maps at 9.94 Hz and 2.00 Hz, respectively, with a median local mapping latency of 32.4 ms. These runtime results demonstrate the real-time feasibility of selective visual state updates alongside multi-view semantic mapping under challenging off-road conditions. The code and related resources are available at: https://github.com/zihanPan-HIT/QVS-LIVO.

cs.RO

新论文 · v1arXiv:2611.16175

Stack more levels: how to get general and human-like Mario playing

Shinichi Arimura, Yuchen Li, Julian Togelius

原文摘要

Super Mario Bros. is widely used in game AI and procedural content generation (PCG), yet it remains unclear whether a model-free agent can reliably win unseen levels. To address this question, we train Proximal Policy Optimization (PPO) agents on increasingly large sets of PCG-generated Mario levels and evaluate their generalization on 1000 held-out test levels. We then shape competent PPO policies into three gameplay archetypes---runner, killer, and collector. Finally, we fine-tune these PPO policies using Diffusion-Reward Adversarial Imitation Learning (DRAIL) with human gameplay demonstrations. We find that increasing the number of distinct PCG-generated training levels generally improves unseen-level performance, and that fine-tuning PPO policies with DRAIL increases action-level human-likeness while preserving much of the persona induced by PPO pretraining.

cs.AI

新论文 · v1arXiv:2611.15777

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

Lichen Li, Ziping Dong, Sicheng Feng, Qi Li, Xinchao Wang

原文摘要

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.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2601.16764

ReLU Networks for Model Predictive Control: Network Complexity and Performance Guarantees

Xingchen Li, Keyou You

原文摘要

Recent years have witnessed a resurgence in using ReLU neural networks (NNs) to represent model predictive control (MPC) policies. However, determining the sufficient network complexity to ensure closed-loop guarantees remains a fundamental open problem. This involves a critical precision-complexity trade-off: undersized networks may fail to capture the MPC policy, while oversized ones may outweigh the benefits of ReLU network approximation. In this work, we project the MPC actions onto a tightened constraint set to satisfy the hard constraints, and establish a state-dependent Lipschitz continuity property for the optimal MPC cost function, which enables sharp convergence analysis of the closed-loop system. For the first time, we derive explicit bounds on ReLU network width and depth for approximating MPC policies with closed-loop guarantees. To reduce network complexity for the convergence to user-specified target sets, we propose a non-uniform error framework with a state-aware scaling function to adaptively adjust both the input and output of the ReLU network. Our contributions provide a foundational step toward certifiable ReLU NN-based MPC.

eess.SY · cs.LG · math.OC

新论文 · v1arXiv:2611.14980

CoLFA: Collaboration-Guided Lightweight Failure Attribution for LLM-Based Multi-Agent Systems

Yufei Luo, Yuchen Ling, Chunrong Fang

原文摘要

Failure attribution in multi-agent systems requires tracing error formation to identify the decisive error step and the responsible agent. However, agents' division of work and information exchange lead to Interleaved Steps and Cluttered Content, requiring models to link executions and check details in lengthy records. This makes it difficult to balance localization accuracy and token cost. We find that multi-agent collaboration also leaves records of how executions connect and content passes between them as results are formed, providing evidence for tracing error formation. Based on this observation, we propose CoLFA (Collaboration-Guided Lightweight Failure Attribution), which uses collaboration cues to organize the attribution input according to how results are formed, determining which steps are examined and how their content is presented. Through Handoff-Guided Step Expansion and Cross-Referenced Content Organization, CoLFA helps the model focus on examining error formation and the role of each decision while reducing the processing of irrelevant and repeated records. Across five settings spanning Who&When and LongRCA and three backbone models, CoLFA achieves the highest exact step-localization accuracy with the lowest token consumption. Compared with individual baselines in each setting, CoLFA improves accuracy by up to 37.50% and reduces token consumption by up to 97.6%.

cs.CL

版本更新 · v2arXiv:2606.00866

Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI

Tian Xia, Yi Xu, Hanchen Li, Zhifei Li, Xiaokun Chen, Hao Kang, Yifan Qiao, Ion Stoica

原文摘要

Agentic programs alternate between LLM inference and tool calls, each request extending the previous one's context. Program-aware schedulers pin a program's KV cache in GPU HBM across tool calls to avoid re-prefilling it at every step, but as contexts grow, pinned KV cache exceeds HBM, raising program eviction: deciding when a program releases GPU memory and when it returns. Offloading to CPU DRAM lets an evicted program wait out a tool call instead of recomputing its context, but existing schedulers leave DRAM to LRU, so offloaded programs thrash. Making these decisions is hard: tool-call durations vary by orders of magnitude and are unknown in advance. We observe that programs nevertheless stay busy (short tool calls) or idle (long ones) for extended periods, and use a program's idleness, its recent fraction of time in tool calls, as a continuous, relative metric. MORI ranks programs by idleness, keeps the least idle in HBM and the next in DRAM, and drops the rest, enforcing admission control at both tiers under any GPU-to-CPU capacity ratio; it also proactively demotes idle programs to make room for ready ones. On real coding-agent traces, MORI achieves on average 64% higher throughput and 72% lower p90 TTFT than the best offloading baseline under high load.

cs.OS

新论文 · v1arXiv:2611.14017

Personalized Memory Rubrics: Learning What to Remember per User via Rubric-Guided Credit Assignment

Yupeng Han, Kai Zhang, Shuochen Liu, Ze Liu, Xianquan Wang, Zhihong Pan, Xiangyu Zhao, Qi Liu 等 9 位作者

原文摘要

Long-horizon personalized agents maintain an evolving memory by continuously deciding what to add, modify, or discard. However, learning an optimal update policy remains challenging. Conventional training relies solely on terminal question-answering accuracy, yielding a coarse feedback signal that treats all intermediate updates identically. Furthermore, update utility is inherently user-specific, as identical memory actions may yield opposite effects across different user personas. Existing methods fail to address this heterogeneity, relying on globally shared evaluation standards with at most a single scalar intermediate reward. To address these challenges, we propose \textbf{Personalized Memory Rubrics} (\textbf{PMR}), a framework that translates terminal feedback into fine-grained, per-step, and per-user credit assignment. PMR decomposes evaluation into a universal layer capturing cross-persona failure patterns and a per-user adaptive layer modeling individual traits as a specialized delta over the universal baseline. Through \textbf{Rubric-Guided Credit Assignment}, PMR redistributes credit at the token level, selectively amplifying validated decisions on successful trajectories while falling back to standard policy optimization on failed ones to avoid unreliable attribution. The rubric and memory policy \textbf{co-evolve} in a closed loop with anti-circularity guarantees. Crucially, PMR incurs zero inference overhead, operating without any rubric or external judge during deployment. Extensive experiments across four benchmarks demonstrate consistent gains over strong memory-augmented baselines.

cs.AI

版本更新 · v3arXiv:2605.22715

AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim

原文摘要

As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highly dependent on the sensing setup, including body location, mounting position, sensor orientation, device hardware, and sampling protocol. This setup dependence makes it difficult to learn motion representations that transfer across devices and datasets, and limits the broader use of wearable IMUs beyond closed-set recognition. We introduce AnyMo, a geometry-aware framework for setup-agnostic human motion modeling. AnyMo uses physics-grounded IMU simulation over dense body-surface placements to generate diverse and plausible synthetic signals, pre-trains a graph encoder from paired synthetic placement views and masked partial observations, tokenizes multi-position IMU into full-body motion tokens, and aligns these tokens with an LLM for motion-language understanding. We evaluate AnyMo on three complementary tasks: zero-shot activity recognition across 14 unseen downstream datasets, cross-modal retrieval, and wearable IMU motion captioning, where it improves average Accuracy/F1/R@2 by 11.7\%/11.6\%/22.6\% on HAR, increases zero-shot IMU-to-text and text-to-IMU retrieval MRR by 15.9\% and 28.6\%, respectively, and improves zero-shot captioning BERT-F1 by 7.5\%. These results support AnyMo as a generalist model for wearable motion understanding in the wild. Project page: https://anymo-project.github.io.

cs.CV · cs.AI · cs.CL · cs.HC

版本更新 · v3arXiv:2503.00868

Physics-Driven Extraction of Dynamic Fluid Asset from Monocular Video with Generative 3DGS

Zhiwei Zhao, Yin Zhao, Minchen Li, Yixin Hu

原文摘要

Existing methods for dynamic 3D scene synthesis from video rely on per-frame deformation fields optimized through pixel-level reconstruction losses. While effective for closed systems such as elastic solids, these approaches face challenges with open systems like fluids where material continuously enters and exits the scene, topology changes freely, and no stable point correspondence exists across frames. We propose a simulation-driven alternative that optimizes the parameters of a fluid simulator to reproduce dynamics observed in a single-view video, rather than fitting per-point deformation to pixel values. Our framework leverages generative 3D Gaussian Splatting (3DGS) models to obtain initial fluid geometry including unseen surfaces, estimates a physically grounded velocity field from surface motions with a physics-constraint correction algorithm, and converts it into a divergence-free, grid-based representation. A differentiable Affine Particle-In-Cell (APIC) simulation then optimizes effective simulation parameters, such as viscosity, boundary conditions, and inflow/outflow velocities, to match the observed dynamics. Because the dynamics are governed by forward simulation, the output assets are inherently editable, interactive, and temporally extendable, which reconstruction-based approaches cannot readily provide. Stage-wise ablations confirm that each stage is necessary, and hyperparameter sweeps show the pipeline to be robust without sensitive per-scene tuning. Our method handles various liquid fluids, including inviscid and viscous types, demonstrating the potential for automatically creating simulation-ready 3D fluid assets from readily available internet videos.

cs.GR

新论文 · v1arXiv:2611.13662

NIF-VIO: Visual--Inertial Odometry Across Inertial and Non-Inertial Reference Frames

Zichao Shu, Lijun Li, Zhuochen Li, Zetao Chen, Jianyu Wang

原文摘要

Conventional visual--inertial odometry (VIO) assumes that observations from cameras and an inertial measurement unit (IMU) are jointly consistent in an inertial reference frame. However, this assumption breaks down under non-inertial conditions. Inside accelerating or rotating carriers, visual observations of the interior reflect carrier-relative motion, while IMU measurements contain additional carrier-induced components, which can compromise conventional fusion. We therefore present NIF-VIO for localization relative to the local environment across inertial and non-inertial reference frames. It adapts visual--inertial fusion based on measurement consistency. As inertial conditions change, early constraint isolation is combined with local reoptimization to limit error propagation before inconsistency confirmation and repair the affected local geometry. Under non-inertial conditions, a compact model with temporally shared parameters is introduced to account for carrier motion while preserving inertial information that complements visual constraints. Experiments on public benchmarks and a self-collected dataset demonstrate that NIF-VIO achieves competitive performance under inertial conditions and improved localization accuracy and availability under non-inertial conditions.

cs.RO

版本更新 · v6arXiv:2610.16717

Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference

Yuchen Li, Xintong Li, Zongqi Fan, Ken-tye Yong, Nguyen H. Tran

原文摘要

Whether a large language model has a self is usually argued without a way to measure it. We measure a functional self with two levels familiar from biology: a self-index, which marks material as the model's own, as animals tag self-generated signals with a corollary discharge, and self-reference, the ability to recognize what is one's own, as in mirror self-recognition. Our main finding is that language models mark their own messages internally and that recognizing them depends on this mark: no model we tested recognizes its own messages without it, and in the four models we edited, changing the mark removes or creates the recognition. With the same text placed in an Assistant, a User, or a System message of its chat template, Qwen3.8-27B separates its own message from both external ones at all 64 layers and in every held-out text. Asked who wrote a message, it answers "you" with probability 0.77 for its own messages and at most 0.07 for the others. Setting eight coordinates per layer, along which its own message differs most from the same text as a User message, to their User values lowers the rate of "you" to at most 0.05, and the reverse edit makes the model claim a User message, closing at least 41% of the gap. Random directions do neither, and answers about the content stay unchanged. This holds in Qwen3.8-27B without and with thinking, gpt-oss-20b, gpt-oss-120b, and MiMo-V2.6-Distill-Qwen-9B. Across twenty-five open-weight models from fourteen developers, the two levels are nested: no model recognizes its own messages without a self-index (permutation p = 0.004). Without any question, next-token prediction on the model's own message differs from that on the same text in another role, more so as more layers carry the self-index (Spearman rho = 0.82), and the same coordinates carry this difference. These results support the account that self-reference is a readout of a self-index.

cs.CL

新论文 · v1arXiv:2611.13514

Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation

Chang Yu, Siqing Li, Yuanchen Liu, Zhenyu Bu, Luming Yang, Alper Yilmaz

原文摘要

Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the segmentation of such small and irregular lesions. To test this, we propose D$^2$Mamba, which couples non-causal state space duality with deformable Mamba scanning. We evaluate it with five-fold cross-validation on the DDR dataset, comparing against representative segmentation baselines under an identical training protocol, and conduct ablations on each component. D$^2$Mamba achieved the best overall performance, with 33.87% mIoU, 2.99 percentage points above the strongest baseline. The largest gain appeared on MAs, the smallest and most easily missed lesions, where Dice improved by 10.06 percentage points. These results confirm our hypothesis that spatially adaptive state space modeling benefits tiny-lesion segmentation. Code and pretrained weights are available at https://github.com/PUREPANEL1/D2Mamba.

cs.CV · cs.LG

新论文 · v1arXiv:2611.13426

BioMem: Agentic Memory for Biomedical LLM Agents

Mingchen Li, Yongkang Xiao, Rumeng Li, Rui Zhang, Hong Yu

原文摘要

Large language models (LLMs) have demonstrated considerable potential in biomedical applications, while agentic memory systems have emerged as a promising approach to preserving and utilizing information across tasks and interactions. However, a fundamental question remains: how effectively and reliably do these systems retain, retrieve, update, and utilize biomedical information? In this study, we systematically investigate agentic memory in the biomedical domain, focusing on task effectiveness, retrieval quality, information fidelity, and long-term robustness. We evaluate five memory approaches across four LLMs in three representative settings: biomedical knowledge reasoning, clinical prediction, and long-term conversational memory. Our analyses reveal how memory construction, evidence relevance, and conversational history shape downstream biomedical performance, highlighting the distinct challenges of retrieving relevant information, preserving its fidelity, and effectively utilizing it for reasoning. Building on these findings, we introduce Hybrid Memory Retrieval and Utilization (HMRU), a training-free framework that jointly enhances evidence accessibility and task-aware utilization to improve biomedical reasoning and long-term conversational memory. HMRU achieves an average relative improvement of 8.6% across biomedical question-answering and conversational memory benchmarks, with additional gains in selected clinical prediction tasks. It further reduces conversational answer errors by 24.9% and closes 48.0% of the performance gap to full-context inference. Our findings provide a systematic characterization of biomedical agentic memory and practical insights into developing more effective and reliable memory-augmented LLM systems.

cs.CL

版本更新 · v4arXiv:2511.21245

FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision

Chen Ling, Henglin Shi, Hedvig Kjellström

原文摘要

Monocular 3D face reconstruction estimates the parameters of a 3D morphable face model (3DMM) from a single image, providing an explicit geometric representation for facial expression analysis. Owing to the scarcity of paired 2D images and 3D facial meshes, most methods are trained in a self-supervised manner by rendering the predicted face and minimizing image-level reconstruction losses, such as photometric and landmark errors, against the input image. However, these losses enforce visual alignment but do not ensure that the predicted parameters preserve affective information. Recent methods add image-level emotion consistency loss, but it can be satisfied by exaggerating facial deformations. To address these issues, we propose FIELDS (Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision), which learns affect-informative expression representations in the FLAME parameter space. Specifically, FIELDS augments 2D self-supervised reconstruction with scan-derived expression anchoring and a parameter-space emotion loss. During training, scan-fitted targets directly constrain expression-related FLAME parameters to discourage exaggerated deformations, while a jointly trained emotion head uses discrete emotion and continuous valence--arousal annotations to make the predicted parameters informative for affect analysis. Experiments show that FIELDS improves affective utility from the predicted parameters in both within- and cross-dataset settings. Notably, it also achieves lower reconstruction errors overall and across most facial regions than the comparison baselines under both rigid and similarity alignment.

cs.CV

新论文 · v1arXiv:2611.12162

Same Physics, Different Gradients: A State-of-the-Art Report on Differentiable Physics Simulation

Lei Shu, Zizhou Huang, Yunuo Chen, Yifei Li, Tao Du, Minchen Li, Tuur Stuyck, Miles Macklin 等 18 位作者

原文摘要

Differentiable simulation propagates derivatives through a physics simulator, turning animation, system identification, control, and computational design into gradient-based optimization. Engines differ in the physics they model and, less visibly, in which mathematical object they differentiate. We separate two questions the literature conflates. The referent is which object the returned derivative belongs to: the finite computation that executed, the converged equation it approximates, or the continuous dynamics. The realization describes the organization of the backward pass: automatically generated differentiation, an equation-level adjoint solve, or a custom adjoint. The referent defines the target against which exactness is assessed; the implementation determines how accurately that target is approximated. Cost depends on the realization together with how the states needed by the backward pass are retained or recovered. Crossing the axes places every method and engine we classify in a cell, separates claims the literature merges, and shows that the apparent trade-off between exactness and memory follows from how methods have been built rather than from a constraint. A second, orthogonal taxonomy covers contact, where the map is non-smooth. We then ask whether a correct gradient helps. Four mechanisms by which useful gradients are lost are cataloged and measured on one testbed, where the advantage of the exact derivative over the equation-level adjoint depends on where the fitting target comes from as much as on the solver budget, and we review the evidence that zeroth-order methods can outperform simulator gradients in the regimes where those mechanisms act. The model classes, systems techniques and applications are surveyed through this lens, and we close with a reporting checklist, a released diagnostic that computes it, and a research agenda.

cs.GR · cs.CV · cs.LG · cs.RO · math.NA

版本更新 · v2arXiv:2611.08839

Functional Dependency beyond Similarity: Hierarchical Decomposition of Training Data Attribution in Music Generative Models

Changheon Han, Hugh Xuechen Liu, Ashkan Panahi, Kıvanç Tatar

原文摘要

Copyright analysis focuses on the similarity between two works. However, generative AI models learn from training data through functional relations beyond similarity. Training Data Attribution (TDA) estimates the influence of each training instance on a generated output and may serve as a basis for remuneration. However, prior studies find global influence, where a few training instances rank as the most influential for almost every generation. Used directly, TDA scores would distribute part of every remuneration to these instances regardless of what was generated. To address this, we propose a new approach in which TDA scores are decomposed into three levels of influence, namely global indicating the influence of a training data to a trained model, group for its influence on a group of generated outputs (that could be clustered together), and specific for its influence on a single generated output. Our study finds that, across several music generative models and TDA methods, global- and group-level influence is non-negligible in every case. Based on these observations, we propose the term functional dependency for the relation of training data to a trained model or to its outputs. This notion both encompasses and distinguishes dependencies of different scopes, allowing TDA scores to be interpreted as distinct forms of contribution in legal, economic and ethical discussions on remuneration.

cs.CY · cs.LG

新论文 · v1arXiv:2611.12087

Compass 1: Towards Open-World and Persistent Embodied Navigation from Monocular RGB Videos

Hai Zhang, Siqi Liang, Yanjun Guo, Shoufeng Zhang, Yunhao Wang, Hangyu Du, Haoguang Mai, Hongchen Li 等 20 位作者

原文摘要

Embodied navigation requires agents to achieve persistent spatial awareness and long-horizon execution stability in open-world environments. However, existing navigation architectures struggle to sustain both capabilities, remaining effective only over a handful of recent frames. We present Compass 1, the first embodied navigation foundation model to unify language understanding and video generation while enabling memory backtracking through nearly 2mins of visual history. Without altering the underlying architecture, we introduce History Representation, which integrates sparse visual keyframes with an explicit History Representation Map to preserve long-term spatiotemporal context. To effectively leverage this history, we further introduce History Utilization, a structured VQA supervision protocol comprising three categories: task-stage grounding, exploration consistency, and spatiotemporal target retrieval, enabling map-grounded reasoning and stable persistent long-horizon navigation. To fuel this system, we establish a complete annotation pipeline for monocular RGB videos and open-source a massive dataset featuring over 500 hours of high-quality real-world interactions and over 2,000 hours of annotated web videos. Trained mainly on the distribution of 1m height camera, Compass 1 generalizes seamlessly across diverse embodiments and scenarios, ranging from indoor environments to pedestrian-dense streets, spanning wheeled robot at 0.35m, quadruped dog at 0.5m, humanoid at 0.85m, and aerial drone at 1.5m. Compass 1achieves a dominant overall success rate of 79.4% across open-world evaluations, compared to 17.8% for the strongest baseline. It demonstrates exceptional zero-shot execution exceeding 90% on foundational tasks, a 250% boost in exploration, and an unparalleled leap from 0% to 58% in challenging persistent history backtracking.

cs.CV · cs.RO

版本更新 · v2arXiv:2608.24005

Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing

Haotian Zhang, Shucun Wang, Jinze Wu, Liang Ding, Shuochen Liu, Zhenya Huang, Jing Sha, Shijin Wang 等 9 位作者

原文摘要

Knowledge Tracing (KT) aims to assess students' dynamic knowledge states from their learning histories. While most existing KT methods focus on single-domain learning with notable success, real-world learning scenarios often involve multiple domains simultaneously, introducing two critical factors: 1) Cognitive load, arising from managing learning across domains in both temporal and knowledge dimensions. 2) Knowledge transfer, where knowledge states in one domain influence related states both within and across domains. In this paper, we focus on exploring these factors to improve students' knowledge state assessment in multi-domain learning scenarios and propose a novel method incorporating cognitive Load and knowledge Transfer for Multi-domain Knowledge Tracing (LT-MKT). Specifically, to bridge isolated domains, LT-MKT first integrates textual information from questions and their associated concepts to construct a Multi-domain Hierarchical Graph, leveraging the advanced representational capabilities of large language models (LLMs). Then, cross-domain features in both the temporal and knowledge dimensions are explicitly modeled to capture the effects of cognitive load. Additionally, a knowledge transfer module is designed to model the propagation of knowledge states within and across domains. By jointly modeling these factors, LT-MKT enables more accurate prediction of students' future performance. Finally, extensive experiments on real-world datasets demonstrate that our method achieves state-of-the-art performance.

cs.AI

新论文 · v1arXiv:2611.11532

DriveFoundry: Co-Evolving Data and Model for Efficient Closed-Loop Iteration in Autonomous Driving

Ziyang Yao, Yuncheng Jiang, Fang Li, Haochen Liu, Shaoqing Xu, Wen Zhang, Xiangyang Chu, Zibin Guo 等 27 位作者

原文摘要

A driving foundation model must learn reusable decision knowledge from rare critical events and apply it under strict runtime constraints. We introduce DriveFoundry, a closed-loop framework improving iteration efficiency under data and computation budgets by coupling structured causal data refinement with adaptive inference. The Data Engine builds traceable scene-candidate records linking scene evidence and factor-decision relations to candidate trajectories and outcome assessments. Candidate comparisons and counterfactual annotations clarify how scene factors affect behavioral feasibility and preference. Verified model failures guide VLM-assisted annotation and expert correction, refining training data and annotation systems. The model engine, Xiaomi-Drive-o1, unifies Perception, Causation, Action, World, and Value within a shared vision-language backbone to enable cross-task knowledge transfer. Block-wise latent refill passes candidate-specific evidence and predicted visual consequences between task blocks, connecting scene understanding, planning, and evaluation. A learned value-of-computation head selects tasks and allocates latent tokens based on expected benefit and cost, adapting inference to each decision. On PhysicalAI, the 9B model achieves the lowest ADE@1 across evaluated splits and horizons among tested models. In AlpaSim, it outperforms Alpamayo 1.5 across all metrics and achieves lower close-encounter and off-road rates than the 34B Alpamayo 2 Super, while trailing in progress and AlpaSim scores. For the 0.8B variant, joint training reduces 5 s minADE@6 by about 54% without altering the inference path or token budget. Adaptive inference matches full reasoning performance using only 28% of tokens. Real-vehicle tests confirm runtime feasibility, supporting a unified paradigm for learning from critical experience and dynamically allocating computation.

cs.AI

新论文 · v1arXiv:2611.11299

EASE-KV: Diagnosing the Gap Between Memory Availability and Effective Use

Di Lu, Zechen Li, Xuanyu Yue, Jiabo Fan, Hao Xue, Flora D. Salim

原文摘要

Reusable key-value (KV) memory avoids repeatedly prefilling retrieved text, but stored and injected memories do not necessarily become usable evidence. We present EASE-KV, a controlled framework for understanding this gap under fixed candidates and a frozen language model. EASE-KV separates three interfaces: whether required relations are preserved during encoding, whether preserved memories receive appropriate influence during allocation, and whether outcome supervision can identify useful allocations. Matched experiments show that causal encoding improves compositional accuracy by 25.0 percentage points over block-diagonal encoding, while the tested inference-time bridging methods fail to recover the lost contextual information. With unchanged stored states, diagnostic evidence-guided allocation improves LongMemEval accuracy from 31.2% to 38.4%, demonstrating that memory influence can be controlled without re-encoding. However, controllability does not guarantee learnability: binary correctness provides informative reward contrast for 53.0% of sampled query groups, compared with 73.6% under the evaluated shaped-reward setting. These findings show that effective KV memory requires more than retrieval and injection: the required relations must be encoded, preserved memories must receive appropriate influence, and supervision must distinguish better allocations from worse ones.

cs.CL · cs.AI

版本更新 · v3arXiv:2610.01425

Why Does Train-Validation Separation Emerge? Update-Pressure Density Dynamics in Pretrained Backbones

Yuchen Li, Zongqi Fan, Ken-Tye Yong, Nguyen H. Tran

原文摘要

During fine-tuning, training accuracy often continues to improve after validation accuracy levels off, widening the empirical gap. We propose a support-transfer account: early updates reuse broadly shared structure, while later fitting relies increasingly on narrower structure with less benefit for held-out examples. From fixed training probes, we normalize per-example gradient magnitudes and measure their pooled dispersion, $D_{\mathrm{den}}$, and their probe-count-weighted within-class dispersion, $D_{\mathrm{within}}^{\mathrm{wt}}$. A local model gives conditions for dispersion and directional cross-entropy separation to grow together, separating uniform logit scaling; additional decision-boundary conditions characterize accuracy-gap growth. A controlled five-level hierarchy tests the effect of sample-private support. A 240-branch intervention matrix crosses training-progress anchors, batch sizes, private shares, and gradient-differentiation doses. The negative gap dose response is clearer at later training stages and is retained across the four batch sizes. A further 48 branches replicate its direction across additional seeds at a fixed stage and batch. Both normalized readouts are positively associated with the accuracy gap in all 90 language fine-tuning runs across three backbones and six tasks. The same direction holds in all 20 vision runs across four datasets. Together, the controlled hierarchy, targeted intervention, and real-model trajectories support a connection between evolving gradient differentiation and train-validation separation.

cs.LG

新论文 · v1arXiv:2611.10768

BlenderFORGE: Framework for Optimizing Reactive 3D-Graphics Editing Ability of MLLMs

Zilin Guo, Tianrui Zhang, Yi Rong, Yichen Liu, Yuxin Guo, Jingcheng Ni, Lewei Lu, Zehuan Wu 等 9 位作者

原文摘要

Multimodal Large Language Models (MLLMs) have shown promise as interactive agents, yet precise, programmatic 3D graphics editing remains difficult to train because existing systems largely rely on closed-source model APIs and lack deterministic, state-verifiable execution environments. We present BlenderFORGE, a trainable data-environment-optimization framework for open-weight MLLM agents that edit explicit Blender scenes through Blender Python (bpy) code generation. BlenderFORGE targets four fundamental state-verifiable editing task families: object placement, shape-key editing, lighting adjustment, and material modification. It integrates three components: (1) a scalable perturbation-based data generation pipeline built from curated assets and large-scale 3D scene repositories; (2) an isolated Blender Sandbox for deterministic code execution, structured state export, and closed-loop reward computation; and (3) a two-stage training pipeline that uses offline teacher trajectories for cold-start Supervised Fine-Tuning (SFT) and sandbox-computed rewards for multi-turn tool-agentic Reinforcement Learning (AgentLoop-RL). Experiments across the four task families show that the resulting open-weight Qwen3-VL-8B and Qwen3.5-9B BlenderFORGE agents substantially improve over their base models and achieve competitive performance with several zero-shot proprietary MLLM baselines on selected metrics. Additional cross-benchmark evaluations and camera-reframing experiments provide evidence of transfer beyond the original training setting.

cs.AI

版本更新 · v2arXiv:2608.00967

TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents

Jingyu Sun, Yuyang Xue, Mingyang Li, Zhengtao Yao, Jiachen Li, Yang Cui, Wenhao Cai, Haozhe Liu 等 12 位作者

原文摘要

Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable, updatable, and diagnostically transparent. Existing memory-augmented agents often store memories as isolated records or overwritable states, making it difficult to preserve how information originates, evolves, conflicts, or becomes obsolete over time. We propose \textbf{TrajWiki}, a trajectory-based memory framework for long-horizon conversational agents. Instead of treating memory as static entries, TrajWiki represents each memory as a source-grounded evolution trajectory, maintained through immutable episodic snapshots and claim-level operations such as \texttt{ADD}, \texttt{REVISE}, and \texttt{DEPRECATE}. To reduce fragmentation and retrieval cost, TrajWiki further introduces \textbf{Memory Wiki}, a persistent intermediate layer that incrementally compiles dialogue history into structured and interlinked wiki pages capturing salient entities, events, quantities, topics, and conflicts. At inference time, queries are routed hierarchically from relevant wiki pages to linked memory trajectories, then to corresponding snapshots and source messages for evidence-grounded answer synthesis. Experiments on LoCoMo and MedMT show that TrajWiki improves long-horizon dialogue performance across both open-source and closed-source LLM backbones, while providing greater interpretability and diagnostic visibility into memory evolution, retrieval failures, and answer generation.

cs.AI

新论文 · v1arXiv:2611.10566

Online Geometric Consistency Assessment of LiDAR Measurements via Recursive Bayesian Comparison

Mingqiao Han, Qigeng Duan, Xuchen Liu, Jinqiang Cui, Xi Chen, Ben M. Chen

原文摘要

LiDAR-based localization and mapping systems produce registered point clouds that serve as geometric measurements for downstream estimation and navigation. Registration errors introduce duplicated surfaces and structural deformation into these measurements. In the absence of an independent reference, online assessment relies on geometry accumulated from earlier measurements. Such assessment requires tolerance to sampling variation and an accumulation process in which observations enter the history only after evaluation. We therefore formulate a recursive Bayesian comparison that couples geometric assessment with history maintenance. A Normal-Inverse-Wishart model represents historical voxel geometry and its uncertainty, while a weak isotropic reference adapts to current sampling. Comparing the marginal predictive support of the same current points under both models yields Normalized Drift Evidence (NDE). Assessment precedes assimilation: positive NDE triggers an alarm and preserves the preceding historical state; otherwise, the current observations update the history. Across 14 real-world sequences totaling approximately 73 min from four platform types, alarms identified all nine corrupted sequences and were absent from all five consistent sequences. In four representative scenarios with event references, first alarms occurred within 0.9 s of the reference times, with no preceding alarms. Cross-backend evaluation demonstrates consistent responses to reconstructed geometry. Ablation and controlled perturbation results establish the roles of uncertainty modeling, recursive history, displacement, and geometric support. Mean processing time is 4.2--6.1 ms per update at 1 Hz. In ten UAV trials, alarms initiated odometry isolation, landing, relocalization, and mission continuation.

cs.RO · eess.SY

版本更新 · v2arXiv:2605.05403

When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models

Jiechen Li, Catherine A. Barry, Rishika Randev, Janet Chen, Ella Jorgensen, Brinnae Bent

原文摘要

This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture overt forms of the phenomenon but leave subtler boundary failures involving epistemic integrity and social alignment underspecified. We argue that sycophancy should be defined not by agreement or factual incorrectness alone, but by cue-driven degradation of epistemic integrity. To clarify this boundary, we propose a three-condition decision rule requiring (1) a user cue, (2) a model response that shifts toward that cue, and (3) a resulting degradation of epistemic integrity. Building on this definition, we also introduce a taxonomy consisting of alignment targets, mechanisms, and severity to characterize cases identified as sycophantic. An initial 48-item annotation pilot provides preliminary evidence that the framework can be operationalized using structured guidelines, although broader empirical validation remains necessary. The paper concludes by discussing implications for alignment evaluation, including boundary-aware assessment, structured rubrics, and mitigation strategies, while situating these proposals alongside alternative views of sycophancy.

cs.AI

版本更新 · v3arXiv:2602.07738

Learnable Chernoff Baselines for Inference-Time Alignment

Sunil Madhow, Yuchen Liang, Ness Shroff, Yingbin Liang, Yu-Xiang Wang

原文摘要

We study inference-time reward-guided alignment for generative models. Existing methods often rely on either architecture-specific adaptations or computationally costly inference procedures. We introduce Learnable Chernoff Baselines (LCBs) as a method for efficiently and approximately sampling from the exponentially tilted kernels that arise from KL-regularized reward alignment. Using only black-box sampling access to the pretrained model, LCBs implement a form of rejection sampling with adaptively selected acceptance probabilities, which allows fine-grained control over inference-compute scaling. We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling while using substantially fewer queries to the pretrained model.

cs.LG · cs.AI