跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2新增论文
+2其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 04:00 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 04:47 — 2026-11-13 04:47（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：2026-11-13 04:00最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

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。

21,675 已收录论文18,323 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 5,218 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 03:58（北京时间）
新论文 · v1arXiv:2611.12291

Representational Alignment between Deep Neural Networks and Human Brain in Speech Processing under Audiovisual Noise

Cheng Luo, Jian Zhu, Zhoujian Sun, Yunyi Qi, Yu Qi, Wenhui Sun, Wenyuan Yu

原文摘要

Speech comprehension in the human brain is an incremental process that begins with acoustic processing and advances to linguistic processing. While recent studies have revealed that the hierarchy of deep neural networks (DNNs) correlates with the ascending auditory pathway, the exact nature of this DNN-brain alignment remains underexplored. In this study, we investigate how DNN representations align with the brain's acoustic-to-linguistic processing. Specifically, we employed neural encoding models to simulate neural responses to acoustic (i.e., speech and noise envelope) and linguistic features (i.e., word onset and surprisal). By applying representational similarity analysis (RSA), we quantified the similarity between these neural responses and the DNN embeddings generated by a pre-trained automatic speech recognition (ASR) model, both before and after fine-tuning on audiovisual noisy data. Our results demonstrate significant DNN-brain alignment: embeddings from shallow layers exhibit higher similarity to neural responses associated with acoustic features, while those from deeper layers align more closely with neural responses related to linguistic features. Importantly, the fine-tuning process enhances this alignment by improving noise processing in shallower layers and refining linguistic representations in deeper layers. These results suggest that fine-tuned DNN models can naturally develop human-like processing patterns in noisy environments, highlighting a functional alignment between the human brain and DNNs in speech representation.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12288

ForgeSystem: An Architecture for Demand-Specific Artefact Production with AI Agents

Qingfeng He, Zhui Zhu, Yaojian Chen, Shangzhan Li, Leshan Li, Tingjian Zhang, Qian Xie, Yuxuan Li 等 10 位作者

原文摘要

General-purpose software serves many different demands, but this flexibility costs performance and efficiency on any specific demand. Software tailored to a specific demand avoids these losses, yet developing it requires substantial time and effort from human experts. AI agents offer an alternative: they can design, implement and test artefacts tailored to individual demands. We call this production paradigm Forge. Forging for a demand is economically justified when the cumulative benefit of specialisation exceeds the total cost of construction, verification and maintenance. To make Forge a repeatable production process, we propose ForgeSystem, which consists of a control layer, a forge loop and a recursive self-improvement (RSI) loop. The control layer selects which artefact serves each demand and decides which demands to forge, when to forge them and from which starting point; the forge loop iterates between production and verification until a candidate artefact passes verification; and the RSI loop draws on accumulated production records to supply starting points, refine the harness and train models. We implement ForgeSystem for training frameworks, decoding megakernels and individual computational kernels. Forged training engines reach 1.047-1.332x the model-FLOPs utilisation of their reference frameworks, forged megakernels achieve a geometric-mean decoding speedup of 1.21x over SGLang across thirteen configurations, and forged kernels match or exceed expert libraries in eighteen of twenty-two configurations, while satisfying task-specific quality requirements. Controlled comparisons show that explicit quality requirements steer agents towards optimisations that preserve training quality. We also discuss a gradual transition to Forge through service routing, and how demand-specific production may shift value accumulation and trust towards production systems.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.37311

ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents

Haohao Qu, Yongcheng Jing, Chun Hin Chan, Shanru Lin, Wenqi Fan, Dacheng Tao

原文摘要

Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative agents autonomously perceive web platforms, reason over user preferences, and execute decisions. However, existing RecAgents still suffer from two critical limitations: brittle item perception based on noisy item pages, and inefficient long-context reasoning over extended user histories and multi-step interaction traces. To address these challenges, we propose a recommendation-agent framework, termed ReMem, that combines OCR-based multimodal perception with time-evolving dynamic memory. Instead of parsing raw HTML, ReMem observes item-page screenshots and uses an OCR tool to produce structured textual evidence for the reasoning backbone. To support long-horizon preference modeling, ReMem further introduces a chunk-wise sequential update strategy that maintains a bounded textual memory while processing histories longer than the backbone context window; with fixed chunk and memory budgets, the number of update calls grows linearly with history length. This design allows the agent to preserve evolving user preferences without relying on external memory modules or disrupting the standard autoregressive generation process. To train the dynamic memory updater, we further develop a multi-memory GRPO variant whose reward combines recommendation-specific information with final-task metrics. Experiments on three Amazon-derived datasets and a controlled post-retrieval protocol show an average relative improvement of 7.58% over the strongest reported baseline across searching, ranking, and judging tasks.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.35110

Understanding and Repairing Cooperative Perception under Adverse Weather

Mengxu Ma, Linshan Yan, Kailong Zhang, Ruiyang Guo, Dagang Shen, Yichen Fan, Hongping Gan

原文摘要

A cooperative detector can lose a correct vehicle detection when surrounding LiDAR measurements change, even if the returns on the vehicle remain unchanged. We study this failure as Weather-Induced Context Interference. On our CoInfra development set, controlled removal outside annotated object boxes turns 22.1% of V2X-ViT's previously correct detections into misses. Restoring network features around the objects to their values before removal recovers 98.6% of these misses. The same restoration in each of three equally sized regions excluding the objects recovers none. Candidate analysis finds accurate boxes that are not selected, while other targets lack well-localized candidates. With paired reference features unavailable at inference, Adverse-Weather Cooperative Repair (AWCR) repairs candidates from current observations. A lightweight Local Correction head generates bounded alternatives, and Quality Selection ranks them alongside original boxes with a correction weight. In V2X-R simulation, AWCR also filters peer returns before detection using Point Classifier trained on generated-point labels. Candidate repair improves mean car BEV AP@0.7 by 4.22 points across three fits on natural adverse-weather CoInfra development inputs and vehicle AP@0.7 by 5.00 points on a rain-affected public recording. It also improves released HEAL, FadeLead, and V2X-DGW detectors with their pretrained weights fixed. On the full V2X-Radar-C validation benchmark, HEAL with AWCR achieves state-of-the-art LiDAR-only cooperative detection performance of 68.22 vehicle BEV AP@0.7.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12286

VLA-MOPD: On-Policy Distillation for Multi-Task VLA Policy Consolidation

Yongxuan Lv, Zhen Fang, Lichen Man, Hao Li, Pu Li, Hengyi Wang, Langfeng Cao, Lin Chen 等 13 位作者

原文摘要

Physical intelligence requires embodied agents to ground language in observations and execute actions while retaining useful skills. Vision-language-action (VLA) policies offer a shared interface, but task-specific post-training often produces separate specialists. Consolidation is difficult: mixed-task reinforcement learning provides sparse trajectory-level credit, while offline distillation may miss student-visited observations and endpoint distillation does not supervise intermediate action-generation states. We introduce VLA Multi-teacher On-Policy Distillation (VLA-MOPD), a protocol for consolidating flow-matching VLA specialists. After acquiring task or suite experts, a shared student collects robot rollouts and queries the instruction-routed frozen teacher at each visited observation and intermediate ordinary differential equation (ODE) state. Detached per-flow-step transition targets supervise valid action chunks through a masked local matching loss; an optional reference-policy term supports retention on other tasks. Starting from one trajectory per LIBERO task, VLA-MOPD raises mean success-once from 75.4% to 98.9%, compared with 98.15% for endpoint action distillation. It improves mean RoboTwin 2.0 success from 73.0% to 89.3%; on a Piper robot, two consolidation rounds improve average success from 70.0% to 90.0%. In a near-matched Spatial-adaptation study, reference matching limits the Object suite decrease to 3.0 points, versus 13.2 without the reference term.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12285

Learning Evidence-Grounded Reasoning for Context-Aware Time Series Forecasting

Xingpeng Gao, Mingyue Cheng, Daoyu Wang, Huajian Zhang, Xiaoyu Tao

原文摘要

LLM-driven time series forecasting has become increasingly promising by leveraging contextual features to generate future values directly or refine forecast priors. However, incorporating contextual features alone does not ensure that models can identify which features matter for forecasting and understand what they suggest about future dynamics. We argue that the fundamental challenge is how to extract predictive evidence from contextual features and when and how to leverage it to guide forecasting decisions. In this paper, we propose CastReasoner, an evidence-grounded reasoning model for context-aware time series forecasting. Specifically, CastReasoner uses a structured chain of thought (CoT) to extract predictive evidence from contextual features, infer the future dynamics suggested by this evidence, and assess these dynamics against the forecast prior to guide adaptive forecasting decisions. To enable this capability, we design a reasoning-centric two-stage post-training framework including supervised fine-tuning (SFT) and reinforcement learning (RL). First, we synthesize reasoning trajectories through controllable multi-teacher guidance and select high-quality ones using a novel student-aware difficulty metric. Second, we design fine-grained multi-objective rewards to further improve reasoning and forecasting. To address heterogeneous learning needs across domains in both stages, we introduce a convergence-guided data balancing strategy. Through this two-stage training, CastReasoner improves both reasoning quality and predictive accuracy. Extensive experiments across multi-domain forecasting benchmarks demonstrate that CastReasoner achieves superior forecasting performance.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.03469

IKOD: Image-Attention-Guided Key-Value Merging against Object Hallucination in the Decoding of Large Vision-Language Models

Jiabing Yang, Chenhang Cui, Yixiang Chen, Tao Yu, Yan Huang, Liang Wang

原文摘要

Large vision-language models (LVLMs) exhibit strong visual understanding and language generation capabilities yet remain prone to object hallucination, producing plausible descriptions unsupported by the input image. Analyzing generation dynamics across eight diverse LVLMs, we observe that cross-modal visual attention steadily decays as generation unfolds because appended text tokens continuously expand the softmax denominator; consequently, hallucinated objects consistently appear later and under lower image attention than grounded mentions. Unlike existing training-free remedies that rely on input perturbations or external models, we propose IKOD (Image-attention-guided Key-value merging against Object hallucination in Decoding), a collaborative decoder that directly compresses the competing text context within the native key-value (KV) cache. At each step, IKOD keeps visual tokens intact and merges low-attention text entries into a compact auxiliary cache, fusing the resulting image-focused distribution with the base branch to correct ungrounded predictions while preserving linguistic fluency. An adaptive variant (IKOD-A) further schedules collaboration strength online from the measured attention decay under a single universal configuration. Extensive experiments across hallucination and general multimodal benchmarks on eight diverse LVLMs demonstrate that IKOD and IKOD-A consistently mitigate object hallucination while preserving object recall and general multimodal capabilities at minimal inference cost. Code is available at https://github.com/jiabingyang01/IKOD.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2509.21190

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy

Tian Lan, Hao Duong Le, Jinbo Li, Wenjun He, Meng Wang, Chenghao Liu, Chen Zhang

原文摘要

Time series anomaly detection (TSAD) is a critical task, but developing models that generalize to unseen data in a zero-shot manner remains challenging. Existing foundation models for TSAD often rely on reconstruction-error scoring at inference time, which can miss subtle anomalies that are well reconstructed and can falsely flag complex but normal patterns in unseen domains. We introduce TimeRCD, a foundation model for TSAD built on Relative Context Discrepancy (RCD), a pre-training paradigm that trains the model to detect anomalies by comparing a query pattern with its surrounding context. This relational formulation, implemented with a standard Transformer architecture, enables the model to infer normality from the input context rather than relying on fixed global normal patterns. We further construct a large-scale synthetic corpus with context-dependent anomaly labels to provide supervised pre-training signals for RCD. Experiments across diverse benchmarks show that TimeRCD outperforms existing general-purpose and anomaly-specific foundation models in most zero-shot TSAD settings, while remaining competitive with dataset-specific full-shot baselines. These results provide empirical evidence that RCD is an effective direction for building robust and generalizable TSAD models.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.25780

A Judge Agent Closes the Reliability Gap in AI-Generated Scientific Simulation

Chengshuai Yang

原文摘要

Large language models can generate scientific simulation code, but the generated code silently fails on most non-textbook problems. We show that classical mathematical validation -- well-posedness, convergence, and error certification -- can be fully automated by a Judge Agent, reducing the silent-failure rate from 42% to 1.5% across 134 test cases spanning 12 scientific domains. The headline result comes from a prospective benchmark: 72 blinded tasks submitted by 12 independent scientists yield an 89% success rate (95% CI: [80%, 95%]) with automated error bounds, versus 53% without the Judge. On clinical CT (the only powered experiment, n = 200), the pipeline reaches 99% of expert quality. The residual 1.5% concentrates at bifurcation points where certifiability breaks down. We formalize this boundary through the simulability class S and introduce spec.md, a structured specification format that makes any scientific computation problem machine-readable and solver-independent. Code, data, and all 72 benchmark tasks are publicly archived.

cs.SE · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12232

ECOS: Environment-Calibrated On-Policy Self-Distillation for Language Agents

Chenhao Zhang, Zhongan Wang, Mingxuan Li, Hehe Fan, Zheng Zhu, Ming Li

原文摘要

On-policy self-distillation lets a language agent act as its own Teacher by conditioning on privileged context such as skills written from its own trajectories. Its guidance, however, is weighted by how much this context shifts token likelihoods rather than by whether it improves behavior, so errors in self-written skills return through later updates. We propose environment-calibrated on-policy self-distillation, which uses environmental outcomes to decide how much to trust the Teacher's current guidance and which self-written skills to reinforce. Command-level advantages, estimated by comparing commands executed at similar observations, scale each Teacher preference and reward reflections and skills whose induced preferences favor higher-advantage commands. Without skills at inference, 3B and 7B agents reach 90.5% and 93.3% macro success on seen ALFWorld tasks and 75.5% and 80.5% success on WebShop. On unseen ALFWorld tasks, they outperform GRPO under the same protocol by 11.0 and 7.6 percentage points, respectively. In an ablation study, supervising only executable commands rather than the Actor's full response raises 3B WebShop success from 52.3% to 75.0%.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.08277

Adaptively Incorporating Directional Hints into Zeroth-Order Optimization

Alexander Ryabchenko, Jian Qian, Wenlong Mou

原文摘要

We study zeroth-order optimization of nonconvex functions with the aid of directional hints, which are cheap but potentially inaccurate approximations of the true gradient direction, given by linear subspaces at each iteration. To leverage these hints adaptively while maintaining robustness to their quality, we introduce Control-Variate Zeroth-Order Descent (CV-ZOD), a new framework that refines the classical zeroth-order gradient estimator with a control variate that can be set based on the directional hints. We first show that the oracle algorithm that optimally sets the reference vector and step size at each iteration achieves a convergence rate that interpolates between the first-order $O(1/T)$ rate and the zeroth-order $O(d/T)$ rate, depending on the quality of the hints along the trajectory. We then develop a practical variant of CV-ZOD that achieves the same oracle guarantee up to logarithmic factors, without any prior knowledge of the hint quality. We validate the method empirically on simulation-based scientific optimization tasks, demonstrating sustained progress on nonconvex landscapes where zeroth-order descent is slower and existing guided methods stall as guidance deteriorates.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12200

Learning to Act with World Models by Valuing What Comes Next

Chenghao Gao, Zhi Zhang, Dian Jin, Yihe Pan, Doudou Zhou

原文摘要

A sparse terminal reward tells an agent little about its steps. Much of the missing information is implicit in the environment's dynamics, because each state transition can change the conditions for success long before the reward arrives. A world model trained on real transitions can learn to predict what each action changes, but a predicted observation does not by itself show whether success has become more likely. With a binary terminal reward, PPO's critic makes this judgment by estimating the current policy's probability of success, but only for states the agent reaches. Our method, WM-PPO, elegantly brings the two together. For each action the policy samples, executed or not, the world model predicts the next observation and the critic values the predicted successor. In the policy channel, comparisons among these values give the policy auxiliary advantages; in the value channel, their mean gives the critic an auxiliary target. A shared gate weights both channels according to how reliably comparisons with similar margins predicted real outcomes earlier in training. The policy, critic and world model all learn from the agent's own interaction, with no teacher or privileged information, and only the policy is used at inference. With a comparable number of real environment steps, WM-PPO raises success from PPO's 63.5% to 87.5% on ALFWorld and from 39.3% to 52.9% on ScienceWorld. It matches the strongest PPO refinements we tested on ALFWorld and exceeds the best of them by 6.5 points on ScienceWorld. The trained policy more often completes prerequisite steps before placing an object or committing to an answer.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.21743

Pairwise AUC Optimization Needs Corrective Power: A Unified View

Jia Chen, Zhiyong Yang, Shilong Bao, Qianqian Xu, Qingming Huang

原文摘要

Direct pairwise AUC-surrogate training is attractive because it trains toward the ranking metric used at test time, especially under class imbalance. This creates a direct alignment between the training objective and the evaluation metric, but such metric alignment alone does not guarantee that stochastic training remains corrective. We study this gap through Corrective Power: whether pairwise mini-batch updates produce stronger and more reliable improvements for more severe positive-negative ranking errors. Our main observation is that direct pairwise training can enter regions where severe errors remain common but no longer produce useful corrective motion. In such regions, even the mini-batch noise that would normally help SGD move along the steepest severe-error correction direction can become much weaker. In this paper, we seek a theoretical explanation for this by exploring the degenerate property of the U-statistics formed from the pairwise gradients therein. Our results provide a mechanistic explanation for several empirical patterns: (a) squared-hinge loss is often an effective AUC surrogate; (b) cross-entropy warm-up can help models that enter the AUC phase from a poor starting region; and (c) parameter-efficient fine-tuning from a pretrained model can reduce that need by starting closer to a favorable ranking geometry. Experiments on 8 CV tasks and 8 NLP tasks, using ResNet50, DenseNet121, DistilBERT-base, and Qwen2.5-1.5B-Instruct, support these predictions.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13036

CapBuddy: Efficient Physical Memory Management for Capability-based Resource-controlling Microkernel

Zhuang Lu, Guangtao Zhu, Shijun Zhao, Qianying Zhang, Lixin Chen, Zekun Xu, Wu Luo, Rui Hou

原文摘要

Capability-based resource-controlling microkernels securely multiplex hardware by exposing low-level resource abstractions guarded by capability systems. Such a design helps provide an application-specific resource management policy to achieve high performance without sacrificing security. However, the misuse of capability-protected secure abstractions can introduce performance overhead in user-level resource management, affecting the runtime performance of dynamic applications in emerging scenarios. In this paper, we focus on the secure abstraction of physical memory in microkernels with capability-based resource management delegation to investigate an appropriate design for dynamic memory management. We propose CapBuddy, an approach to building an efficient buddy system on capability-protected secure abstractions of memory, to bypass the performance overhead of the capability system by offloading functionalities that can run offline from the critical path of serving a memory request. We implemented a prototype system on the seL4 library OS, and the evaluation results show that our approach improves the performance of the seL4 user-level buddy system by 20 to 54.5 times and achieves the same order of magnitude as Linux. Further burst experiments evaluate CapBuddy's scalability and show that it maintains low median allocation latency as the number of concurrent clients increases.

cs.OS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12177

Embodied First Exam

Kangrui Wang, Qineng Wang, Changhe Chen, Pingyue Zhang, Chi Gui, Feishi Wang, Canyu Chen, Wenli Xiao 等 30 位作者

原文摘要

Early successes on agentic robotics point to a potential paradigm shift toward using coding agents to control robots. Existing robotics benchmarks are built around visuomotor policy learning, leaving it open whether coding agents can reliably control diverse robots under physical-world constraints. We therefore introduce the Embodied First Exam, a unified, comprehensive, and agent-native evaluation framework where coding agents can choose their own control approach: direct control, code to control, or train a policy to control. We hope it serves as a first exam for coding agents before they enter the physical world, with 1,156 tasks in 35 suites on 47 robots, including 9 new suites that go beyond pick-and-place to spatial puzzles, dexterous manipulation, multi-robot interaction, dynamic whole-body control, and sim-to-sim engineering. Each task can be run in up to three evaluation settings. The Standard Setting mimics the real world: the agent receives only sensor observations and, by default, cannot reset the environment. Its Realtime variant keeps the environment running while the agent reasons. The Privileged Setting gives the agent access to the full simulator state and unlimited resets, allowing it to search for an oracle solution for training purposes. Success rates in this setting serve as an approximate upper bound. On the 456 core tasks, the strongest of eight agents, GPT-6 Astra in Codex, achieves a success rate of 34% in the Standard Setting, leaving much room for improvement. To see where agents fail, we label the stage at which failed attempts go wrong and compare failures across agents, settings, and stage categories.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12175

GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation

Jinghe Wang, Xinrui Cao, Duo Wu, Chenghao Gu, Yong Zhong, Linjia Kang, Tianyi Xiong, Zhi Wang

原文摘要

Robotic manipulation has advanced rapidly in mapping visual observations and language instructions to actions. However, reliable manipulation in open-world environments requires robust spatial understanding: the ability to identify targets in complex layouts (spatial reasoning) and adapt to scenes that continuously evolve through interaction (spatial memory). Yet existing embodied benchmarks fall short in evaluating spatial understanding: they often introduce strong visual cues that bypass spatial reasoning, and focus on static scenes that offer little insight into an agent's capacity for spatial memory. To address this gap, we introduce GeoMind, a systematic benchmark for structured spatial understanding through tabletop manipulation. GeoMind comprises 54 evaluated task variants organized around spatial reasoning and spatial memory. It also incorporates a scalable pipeline that automates the generation and annotation of task instances with verified targets and executable interactions. Extensive evaluations across diverse embodied agents reveal their consistent weaknesses in spatial understanding. Our findings highlight that these agents struggle to track identities after spatial changes and convert relational or geometric constraints into executable actions. We release the GeoMind benchmark at https://github.com/Notfound-JH/GEOMIND-benchmark.git.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.14948

LFM4Ads: Large Foundation Model for Ads Recommendation

Jie Jiang, Shangyu Zhang, Shijie Quan, Zhongren Wang, Tianqu Zhuang, Junwei Pan, Bo Fu, Yilong Sun 等 35 位作者

原文摘要

Recent work leverages large-scale pretrained foundation models (FMs) to transfer generalizable representations to downstream advertising tasks. Most existing approaches transfer user representations (URs) and item representations (IRs), while underutilizing the user-item cross representations (CRs) generated by deeper interaction layers. Although a recent work transfers target-aware embeddings (TAEs), it requires real-time upstream FM inference alongside the downstream, introducing additional engineering complexity and overhead. To address these limitations, we propose Large Foundation Model for Ads Recommendation (LFM4Ads), an efficient pretrain-then-transfer paradigm for cross-domain ad recommendation. LFM4Ads jointly exploits URs, IRs, and CRs from the upstream FM. It extracts sample-level CRs from pretrained interaction layers and aggregates them into user-level CRs using a time-aware exponential moving average, thereby decoupling upstream inference from downstream online serving. To use CRs efficiently, we propose three downstream usages at different levels of granularity: feature-level gating to fuse CRs into downstream embeddings, module-level fine-tuning to yield downstream CRs, and model-level retrieval by matching CRs with IRs. LFM4Ads has been deployed on Tencent's advertising platform since Q4 2024. It has supported 10+ launches across major scenarios, yielding a platform-wide gross merchandise value (GMV) lift of 2.45% and annual revenue gains in the hundreds of millions of dollars. Offline experiments on KuaiRand-1K further demonstrate our effectiveness. Our code is available at https://github.com/ZhuangQu/LFM4Ads.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41158

Lifelong Learning of Scheduling Rules with Surrogate-assisted Genetic Programming for Dynamic Flexible Job Shop Scheduling

Luyao Zhu, Fangfang Zhang, Yi Mei, Ke Chen, Mengjie Zhang

原文摘要

Genetic programming (GP) has been widely used to learn scheduling rules for dynamic flexible job shop scheduling (DFJSS). However, trained rules tend to only generalise to tasks of similar scales and distributions, and when task characteristics change, learned rules often suffer significant performance degradation. Moreover, fine-tuning pre-trained rules on new tasks often leads to catastrophic forgetting, where prior knowledge is lost. This motivates the need for GP methods that can adapt to new tasks while preserving past knowledge, leading to a lifelong learning paradigm. However, lifelong learning in GP for DFJSS remains largely under-explored. To address this gap, this paper proposes a surrogate-assisted GP method for lifelong learning to handle sequential heterogeneous DFJSS tasks with job or batch arrivals. The framework includes three key components: an adaptive two-stage training strategy to balance plasticity and stability, a task-similarity-based weighting mechanism to regulate knowledge reuse, and an improved surrogate model with distance constraints to enhance estimation accuracy. Experimental results show that the proposed method effectively mitigates catastrophic forgetting while maintaining strong adaptability, outperforming several compared methods and demonstrating the potential of lifelong GP in dynamic scheduling environments.

cs.AI

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
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

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.24209

Displacement Geometry Captures Platonic Shared Reality Across Models and Modalities

Chenming Shang, Yujin Tang, Jun Jie Ou Yang, Ruize Xu, Adam Breuer, Nikhil Singh

原文摘要

The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work finds that the evidence weakens under some conditions. In this paper, we measure what models share through the directions (displacement vectors) between samples. Under a single orthogonal alignment limited to just rotation and reflection, these displacement vectors are substantially preserved across 44 independently trained vision and language encoders spanning modalities and asymmetric capability pairs, consistent with the PRH. Pointwise similarity, however, is lower. Representations split into a shared semantic component that is linearly aligned across models, and a private component that is not, which we interpret as having model-specific capabilities. We trace this geometry to concept-level structure: within a model, parent concepts are orthogonal to their child variation vectors; across models, concept displacements are parallel. We predict (and experiments confirm) that fine-tuning preserves Pointwise similarity but reduces displacement similarity, and relational distillation does the opposite. Because semantics align linearly but capabilities do not, we propose importing capabilities from one model to another using a single cached forward pass through the source. We call this Shadow Casting. As a proof of concept, our ShadowCLIP instantiation outperforms strong fine-tuned baselines at far less compute. A cache can be released alongside open model weights, letting one model's capabilities be downloaded and imported into other models with frozen backbones.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06343

Prism: Bidirectional Self-Teaching for Unified Multimodal Models

Peng Zhang, Qian Chen, Xianyin Zhang, Yimin Tian, Ruite Fei, Dongyi Lv, Lifan Guo, Chi Zhang 等 9 位作者

原文摘要

Unified Multimodal Models (UMMs) aim to support visual understanding and generation within a single model. Existing post-training methods either use understanding as a fixed teacher to improve generation, or rely on ground-truth trajectories to supervise both understanding and generation. Prism instead derives bidirectional supervision from self-generated interleaved rollouts, constructing training targets according to the reliability of their text and image chains. We propose Prism, a bidirectional self-teaching post-training method for UMMs. Like a prism decomposing mixed light, Prism decouples a coupled interleaved trajectory into a text chain and an image chain, assesses the reliability of each chain, and constructs a corresponding training target from their reliability states. Experiments on both SenseNova-U1 and BAGEL show that Prism improves both understanding and generation. On the generation side, GenEval improves from 85.8 to 89.2 (+3.4), and DPG improves from 86.1 to 87.3 (+1.2) on SenseNova-U1. On the understanding side, the total MME score improves from 2282.6 to 2311.6, and MMVP improves from 58.0 to 62.0. Consistent improvements are observed on BAGEL. These results highlight that Prism enables coordinated improvements in generation and understanding by constructing reliability-guided self-training targets from self-generated trajectories, without relying on an external verifier or externally annotated corrected trajectories during target construction. Code is available at https://github.com/aliyun/qwen-dianjin/tree/master/DianJin-Prism.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2604.20133

EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation

Aimin Zhang, Jiajing Guo, Fuwei Jia, Chen Lv, Boyu Wang, Fangzheng Li

原文摘要

Large language model (LLM) agents increasingly rely on reusable skills, but skills are usually written by hand, and letting an agent change them on its own calls for explicit user control. We report on EvoAgent, an evolvable agent framework built for a foreign trade assistant, and share the engineering choices behind it. We organize the agent as a harness of four components (reasoning, context engineering, tools and state) and confine self-improvement to the user's persistent state: profile, memory and skills. Skills are multi-file packages with lazily loaded references, matched in three stages (keyword, embedding, LLM). The main agent can delegate to sub-agents with their own context, and long histories are compressed while an index of recoverable resources is kept. An offline loop reviews completed sessions to update the profile and memory and to propose skills; in the open-source release a skill changes only after the user confirms the proposal. On 172 foreign trade test cases scored by an LLM judge on five dimensions, GPT-5.2 with EvoAgent scored about 28% higher than GPT-5.2 called directly with only the final query. This is a single run judged by the model under test, so it measures the harness as a whole rather than any one mechanism, and swapping in GPT-4.1 or Qwen3.5-35B-A3B lowered the scores relative to calling those models directly. Several mechanisms described here were added after the version we evaluated and are not evaluated. The evaluation data is proprietary, so the results are for reference only. An open-source release of the code, which is not the evaluated business version, is available at https://github.com/Focus-AI-Center/Mentarc-EvoAgent

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12130

Compact and Wide-Force-Range Magnetorheological Hand Exoskeleton for Kinesthetic Feedback in Teleoperation

Xianlong Mai, Rui Yu, Rui Chen, Daniele Leonardis, Wenbo Li, Domenico Chiaradia, Antonio Frisoli, Shuaishuai Sun

原文摘要

Hand kinesthetic feedback is crucial for restoring and enhancing human perception of force and displacement in robotic hand teleoperation. Wide perception range of force feedback is vital in rendering objects of different stiffness, especially for high-stiffness rendering. However, existing approaches struggle to achieve wide range of force feedback while maintaining compact and wearable design. This paper presents a hand exoskeleton system employing magnetorheological (MR) brakes to provide a wide range kinesthetic feedback during teleoperation. The MR brake provides a braking torque ranging from 0.01 to 0.918 Nm, while maintaining a compact structure with a total mass of only 39.8 g. The proposed exoskeleton can render fingertip forces up to 21 N while maintaining back-driving force of 1.01 N. Experimental results show that the system allows users to discriminate object stiffness using kinesthetic feedback alone. In a tele-grasping task, when both conditions achieved a 100% success rate, kinesthetic feedback led to a 28.2% reduction in object contact force compared to visual feedback only, enhancing object safety and operator immersion. Questionnaire results further indicate that kinesthetic feedback improves reliability, realism, and user confidence during teleoperation.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12127

Lost in Rounding: bf16 Recurrent State Makes Hybrid Reasoning Models Think Longer

Yuchuan Weng, Xin Chen, Chi Liu

原文摘要

Hybrid reasoning models interleave attention with recurrent mixers such as Mamba-2 and Gated DeltaNet, whose state is cached between decoding steps. Prior work showed that storing this state in FP16 or INT8 with round-to-nearest (RTN) makes Mamba-2 and GDN hybrids more verbose, and that stochastic rounding (SR) fixes it. We study the other 16-bit format that serving engines expose, bf16, on six open hybrid reasoning models and 590 competition-math problems. With bf16 RTN state, five of six models reason longer (geometric-mean length 1.07x to 1.27x; also under greedy decoding in the two models tested) and hit the 32K token cap more often. On Qwen3.5-9B, cap hits rise from 118 to 223 and accuracy falls from 85.6% to 70.8%. On LiveCodeBench, both models tested also reason longer and lose 12.6 and 13.4 points of pass@1. Rerunning the capped items with a 128K budget halves the accuracy gap but does not close it (93.6% vs. 86.6%): bf16 runs that never finish are twice as common, and 85% of them are exact repetition loops. On Nemotron-Nano-9B-v2, by contrast, 30 of 31 extra caps finish at 128K, so the cost there is mostly extra tokens (exploratory). Same-width bf16 SR removes the length increase in four of five affected models, restores Qwen3.5-9B to 87.6% and brings code length and pass@1 near FP32 levels, so the failure is mostly rounding bias, not missing resolution. With an integer-hash random generator, SR on Qwen3.5-9B matches FP32 on cap hits and accuracy (113 vs. 118; 85.6% for both) at the memory and decoding speed of bf16 RTN. In the Nemotron-Nano-v2 lineage, SR on 25% of heads (an intermediate-decay band) removes the effect, while random heads and the top teacher-forced-KL octiles do not; in Nemotron-3 and Qwen3.5-9B the effect is spread across heads. We recommend that evaluations of hybrid models report the state dtype, cap rate and output length alongside accuracy.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12118

Joi-Bench-Task: Benchmarking Task Coordination in Full-duplex Voice Agents through Interactive Simulation

Xiangheng He, Mingjun Zhao, Zhehao Fan, Zhengjia Li, Xiaopeng Sun, Qingqing Xiao, Haolan Chen, Yu Xu

原文摘要

Full-duplex voice agents enable natural, hands-free interaction, allowing users to refine requests, redirect ongoing work, and seek clarification while the agent is speaking. However, existing voice-agent benchmarks insufficiently isolate coordination between task execution and conversation. We introduce a benchmark that assesses this coordination by examining whether agents track what is being executed, what has been completed, what has been communicated, and what remains to be reported as the conversation evolves. We propose an interactive user simulator that introduces configurable interventions at designated timing in tool execution and spoken result delivery, supporting controllable and reproducible evaluation conditions. We evaluate five leading commercial voice agents along three dimensions: execution responsiveness, coordination under request changes, and coordination under interruptions. Agent evaluations reveal persistent coordination failures. Under request changes, the highest result completion rate is only 55%, indicating difficulty for current voice agents adapting to new requests while preserving earlier obligations. After user interruption, four of the five agents exhibit average information omission rates of at least 23%. These findings highlight task coordination as a central challenge for current voice agents in complex, evolving conversations.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12112

LiveWorkspace: Externalizing Visual Understanding as Persistent Shared State for Screenshot-to-Code Agents

Shijun Xiao, Zonghui Yang, Xinrong Chen, Hao Liu, Wensheng Zhang, Yongqiang Tang

原文摘要

Screenshot-to-Code requires coding agents to sustain visual understanding across code generation, execution, and revision. We introduce LiveWorkspace, a visual coding harness that externalizes this understanding as Shared Visual State (Shared VS), an implementation-independent representation of visual hierarchy, node attributes, and layout relations. LiveWorkspace constructs and retains \textit{Target} from screenshots and recovers \textit{Current} from browser execution in the same schema. Structured Diff and implementation bindings guide code modifications; user edits update \textit{Target} and reuse the alignment loop. Using GPT-5.2 for both methods, LiveWorkspace improves end-to-end Avg by 1.8 points on Design2Code and 2.0 on ScreenBench over a control with matched model-call counts and stagewise budget limits. Further experiments demonstrate reuse of constructed Shared VS across coders and improvements in iterative repair. LiveWorkspace also achieves 93.0\% edit success across 100 controlled editing cases. These findings support treating visual understanding as a persistent shared working state throughout code generation, execution, and modification.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12113

Motion Belief Action: From a Visual Scene Map to Physical Decisions

Dibyendu Ghosh

原文摘要

A robot that works among people must judge what it cannot see: whether an object is still where it was last seen, and whether a pull on a door or drawer is worth its risk. Maps that track object change hold nothing about force, maps of physical properties answer a risk question at a fixed risk level, and vision-language-action models keep no explicit estimate of hidden physics. We propose Motion Belief Action (MBA), a decision layer on the scene map. From how often people move an object and how much force it needs, how much load it holds and whether it is blocked, MBA chooses under a force limit to look again, nudge, open, brace or decline, with its risk set by the task's costs. On real activity in 9 kitchens, it predicts whether an object is still in place better than FreMEn and Perpetua, and decides when to look again at lower cost than these and the persistence filter, because about a quarter of placements end in a pick-up within 30 s. On real pulls of doors and drawers in 17 locations, made by a person with a force-sensing gripper, the map's force estimates decide better than a part-type average. Setting the risk from the costs also beats a published risk rule at its fixed level. In simulation, with the force limit at the training parts' median force, MBA raises SmolVLA's and Octo's scores by declining pulls; most declined door pulls would fail, but on drawers more would have opened, and a part-type average gets about half of this gain. In both, a published risk rule set to the risk these costs imply is MBA's rule for a single pull and decides as well in the main settings. A link between opening and holding force, a probing nudge and an action prior for camera tracking do not help in the main settings, and over the real-pull sweep the nudge costs a little.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12111

GAP: Generalized Adaptation Prior for Dexterous Piano Playing

Jinyi Chen, Hongyi Li, Lei Jiang, Xianwei Liu, Yanhong Liang, Yulin Chen, Yucheng Tao, Yongbin Jin 等 9 位作者

原文摘要

Dexterous hands enable versatile manipulation, but policies trained in simulation often degrade on hardware owing to non-idealities, and the high-dimensional action space makes real-world adaptation costly. Piano playing, which requires precise and coordinated multifinger motion, offers a representative testbed. We propose GAP (Generalized Adaptation Prior for Dexterous Piano Playing), a sample-efficient adaptation framework that learns how to adapt, rather than how to act, during simulation pretraining and transfers this adaptation prior to hardware. Between repeated executions, GAP uses feedback to adjust the actions of the next one: a gradient guidance network learns from paired executions how adjusting actions affects playing performance, and its gradients guide these adjustments. In simulation, GAP yields approximately 2.4 times the F1 scores improvement of the existing fast-adaptation baseline for dexterous piano playing under the same interaction budget. The learned prior also generalizes to musical pieces held out from pretraining. On a physical dexterous hand, the same simulation-pretrained prior improves F1 scores by 3.6%-23% across three pieces of varying difficulty after approximately 7 min of adaptation each. These results suggest a practical route to reduce the real-world interaction needed to deploy dexterous hands.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.12095

From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow

Kun Feng, Chenchen Chu, Yan Liu, Haojie Sun, Jijun Tang, Chen Tian, Shuolin Xiao, Jianping He 等 9 位作者

原文摘要

Biomedical ontologies are structured knowledge systems that must evolve continuously to represent newly emerging knowledge, but their manual maintenance remains time-consuming and laborintensive. Textual definitions are especially costly because they must be readable to humans and compatible with controlled entities, relations, and logical constraints. Large language models (LLMs) offer a promising way to assist ontology engineering tasks, including definition generation. However, textual plausibility does not guarantee knowledge-system compatibility. A generated definition may be fluent and close to a reference definition, yet still fail to ground its implied entities or violate ontology-level constraints. Directly inserting such definitions into ontology libraries may therefore introduce entity-level hallucinations and logical inconsistencies. To address this problem, we propose two structured-knowledge incompatibility metrics, Entity Error Rate (EER) and Logical Inconsistency Rate (LIR), to quantify entity grounding and logical consistency for LLM-generated ontology definitions. We further develop an agentic quality-control (QC) workflow that treats definition generation as an iterative process rather than a direct decoding step: it generates definitions, extracts axioms, checks entity existence and logical consistency, and uses the resulting diagnostics to drive repair loops. Comprehensive experiments on Disease Ontology, Uberon Ontology, and Uberon-ConstraintStress demonstrate that EER and LIR complement conventional reference-based metrics by evaluating whether generated content can be grounded and checked inside the target ontology. The workflow effectively decreases EER while maintaining strong conventional text-generation performance. LIR further exposes sparse ontology-level logical failures that are invisible to text similarity metrics, although their repair remains limited.

cs.AI

查看论文
arXiv ↗PDF ↗