跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描:2026-11-22 14:51 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 16:22 — 2026-11-22 16:22(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:2026-11-22 14:51最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

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

浏览论文库

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

找到 24,181 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 14:49(北京时间)
新论文 · v1arXiv:2611.23961

3DTouch: A Tactile-aware VLA Model with 3D Geometric Relations for Dexterous Manipulation

Xin Zhang, Shiqi Zhang, Siyuan Cao, Juncheng Cai, Yedong Shen, Yuxuan Gao, Dianlong Wen, Kaixue Long 等 12 位作者

原文摘要

In contact-rich dexterous manipulation, occlusion by the fingers and interacting objects obscures local geometry, preventing visual observations from fully capturing contact locations. Visually similar scenes may also differ subtly in the relative positions of interacting objects, leading to different contact states. We propose 3DTouch, a tactile-geometric conditioning approach for vision-language-action (VLA) models. 3DTouch constructs a shared 3D visuo-tactile representation by expressing RGB-D scene points and dense five-finger tactile measurements in the robot-base frame, preserving each taxel's spatial location and force vector. Hand-object and object-object relations derived from hand landmarks and pose-aligned reconstructed surfaces explicitly describe the relative arrangement of interacting entities. Together, these representations condition the VLA action expert on spatially localized contact forces and relative surface geometry, providing explicit cues for contact adjustment and object alignment. We evaluate 3DTouch on five real-world contact-rich dexterous manipulation tasks using a UR7e robot arm equipped with an XHand dexterous hand. 3DTouch improves the average success rate by 42 percentage points over the corresponding VLA baseline and by 20 percentage points over the strongest evaluated alternative. Ablation studies reveal the complementary benefits of scene geometry and spatial tactile feedback, with further gains from shared spatial grounding and explicit geometric relations.

cs.RO

版本更新 · v3arXiv:2602.16169

Unlocking Continuous Diffusion Language Models via Discrete Stochastic Localization

Yunshu Wu, Jiayi Cheng, Longxuan Yu, Partha Thakuria, Rob Brekelmans, Evangelos E. Papalexakis, Greg Ver Steeg

原文摘要

Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that continuous diffusion can effectively model discrete sequences through the joint design of noise parameterization and token representation geometry. We introduce \emph{Discrete Stochastic Localization} (DSL), a continuous-state framework that combines a stochastic localization channel with unit-sphere token embeddings, resulting in a Bayes-optimal denoiser that depends only on the noisy state, without additional timestep conditioning. A single trained denoising network then supports multiple sampling methods, from continuous denoising to masked diffusion, random-order autoregressive generation and hybrid continuous-then-discrete generation. Parallel generation in this continuous-state framework, therefore, need not imply synchronized denoising: some tokens can establish context earlier while others remain open to refinement. Fine-tuning a pretrained MDLM checkpoint with DSL substantially improves generation quality, as measured by MAUVE, on OpenWebText across all step budgets from $T{=}128$ to $T{=}1024$. The same checkpoint supports random-order autoregressive sampling, and a hybrid continuous-then-discrete sampler using as few as $T=48$ total steps, without distillation or further training.

cs.LG · cs.CL

版本更新 · v4arXiv:2608.27821

How do features act in an individual prediction? Separating standalone and interaction effects with a case-based taxonomy

Sejong Oh

原文摘要

Local explanation methods such as SHAP and LIME summarize each feature with a single attribution score, and interaction indices quantify how strongly features interact. Neither tells a user how a feature acts in a given prediction: whether its effect is the same alone and in context, or whether the other features amplify it, make it unnecessary, switch it off or reverse it. We extend case-based feature importance (CBFI), originally a global method, to individual predictions. Evaluating the model in four hybrid states per background sample decomposes the in-context importance of a feature into a standalone and an interaction effect, and a case taxonomy labels each feature of an instance as inactive, standalone, amplified, redundant, gated or reversed. We compare the method with k-SII, TreeSHAP interaction values and the H-statistic on synthetic functions, and study eight real tabular datasets with six model families. On the true functions, the decomposition recovered interactions exactly (correlation 0.99 with the analytic local interaction). On fitted models, pair recovery was slightly below that of dedicated indices (local precision@k 0.86-0.91 versus 0.91-0.95). Interaction values alone could not distinguish substitution from gating, whereas the taxonomy identified both without knowing the partner (accuracy 0.74-0.76); applied to Shapley interaction values, it performed comparably. On real data, 45-57% of feature pairs with nearly identical SHAP values received different labels, and in a medical-insurance model the method showed that the interaction component of smoking changes sign at a body-mass index of 30. Localized CBFI does not detect interactions more accurately than existing indices; what it adds is a decomposition into standalone and interaction effects and a label stating how each feature acts.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.22275

Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration

Ting-Hsuan Chen, Siheng Zhao, Han Jiang, Qi Pan, Louison Lu, Jiaheng Luo, Henghui Bao, Yiyu Chen 等 10 位作者

原文摘要

Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a decentralized framework for long-horizon collaborative multi-humanoid loco-manipulation. At the low level, we develop a multi-agent post-training framework that adapts a humanoid foundation tracking model to physically coupled interactions between humanoids, enabling coordinated decentralized control from local observations alone. At the high level, we train a vision-language planner and design a speech-based leader-follower coordination mechanism to synchronize decentralized execution without network communication. Trained with two identical humanoids, our system scales to teams of up to ten robots and generalizes to heterogeneous teams without retraining. To benchmark these capabilities, we introduce HH-Bench, comprising 12 tasks involving teams of 2 to 10 humanoids, including heterogeneous teams. Systematic evaluations show that Heave-Ho consistently outperforms baseline methods, while real-world experiments demonstrate robust decentralized collaboration across challenging tasks.

cs.RO · cs.CV · cs.LG

新论文 · v1arXiv:2611.23954

SimplePro: A Simple Baseline for Proactive Video Understanding

Yilin Wang, Xiangxi Zheng, Dongxing Mao, Linjie Li, Zhengyuan Yang, Alex Jinpeng Wang

原文摘要

Proactive video understanding requires vision-language models (VLMs) to decide not only what to answer as a video unfolds, but also when newly arrived evidence warrants a response and when to remain silent. Although modern VLMs excel at offline long-video understanding, they struggle in proactive streaming settings, leading prior work to introduce task-specific reinforcement learning or auxiliary triggering modules. We find that explicit reporting rules and structured streaming context substantially improve a frozen VLM's proactive response performance. We exploit this observation to build SIMPLEPRO, a training-free baseline for proactive video understanding. At each decision step, the model combines recent high-resolution frames, bounded historical observations, and prior answer records to determine whether new information warrants a response and, when needed, generate a concise answer. The system then filters consecutive duplicate answers while retaining the raw outputs as context for subsequent decisions. Without any parameter updates or auxiliary triggers, SIMPLEPRO with a 4B backbone consistently outperforms specialized proactive systems across OVO-Bench, StreamingBench-PO, and ProactiveVideoQA. SIMPLEPRO shows overall performance gains as backbone size increases from 2B to 32B. We hope this simple yet effective method will serve as a strong baseline for proactive video understanding, and we will release our code and inference pipeline to support future research.

cs.CV

新论文 · v1arXiv:2611.23953

MitoWorld: A Stochastic World Model of the Single-Cell Cycle under Genetic Perturbation

Ting Long, Xiaojing Sun, Cheng Han, Zhicheng Ji, Yingnian Wu, Jiebo Luo, Heng Fan, Dongfang Liu

原文摘要

A cell observed after a gene knockdown has an uncertain future, both in how its appearance will evolve and when it will divide. Existing approaches predict endpoints or population-level changes without jointly modeling individual trajectories and division timing. In this work, we present MitoWorld, a stochastic world model that generates these future appearances as continuous evolution in a Gaussian reference latent, terminated by a division hazard and converted into images by a conditional diffusion renderer. The ordinary transition provably preserves its Gaussian reference, tying its noise to its dynamics; paired observations identify its discrete transition where stationary marginals cannot. The hazard turns division timing into a survival likelihood that can be tested against real cycle lengths. On 325 held-out MitoCheck tracks spanning 17 knockdowns and a control, MitoWorld lowers FID by 34.6\% and the video metric JEDi by 45.6\% relative to the strongest baselines. Its latent-space prediction intervals achieve near-nominal 90\% coverage, are 35\% narrower than those of a model with freely fitted noise. The hazard also yields cell-cycle length distributions with KS distance close to the model-based finite-sample reference. Testable single-cell stochastic dynamics thus offer a generative tool for time-lapse perturbation screens.

cs.CV · q-bio.QM

版本更新 · v2arXiv:2611.22245

Multi-Agent Memory Inconsistency: Where Factual Conflicts Disappear in LLM Agents

Hejia Zhang, Zhongming Yu, Yimin Ding, Wei-Ting Chen, Hengjia Yu, Wentao Ni, Yijun Liu, Cong Xu 等 12 位作者

原文摘要

Multi-agent delegation lets LLM systems distribute evidence collection across workers with separate contexts. This creates a consistency challenge: facts retrieved by workers may be missing from the evidence available to the lead for a joint conclusion. We introduce a benchmark and evidence-flow profiler for studying multi-agent memory inconsistency through controlled factual conflicts in Harvey LAB document-review tasks. Pooled across three models with comparable generation spending, requiring delegation increases retrieval of both conflicting claims from 50.2% to 68.7% relative to single-agent execution, yet conflict detection falls from 16.2% to 13.2%. Within this setting, workers report both claims for only 35.2% of retrieved pairs, and pooled matched comparisons show higher detection than single-agent execution when one worker reads both claims but lower detection when the claims are split across workers. Worker-to-lead handoffs are a central target for improving conflict detection in multi-agent LLMs.

cs.AI · cs.MA

版本更新 · v2arXiv:2605.20942

Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding

Lena Wild, Katie Z Luo, Marco Pavone

原文摘要

Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-language models (VLMs) offer promising semantic flexibility, they lack the geometric and relational grounding required for precise road reasoning. Conversely, traditional modular systems, e.g., HD maps and topological road graphs, provide structural precision but remain semantically rigid. To bridge this gap, we introduce the Combined Road Substrate (CRS), a graph-grounded framework that makes geometric road structure and open-vocabulary semantics jointly executable in a single representation. CRS enables the automatic generation of compositionally complex and linguistically varied question-answer pairs via recursive graph queries, augmented with a "grounding for free" mechanism that ensures logical traceability to specific map elements, and procedurally extracted chain-of-thought supervision traces. We demonstrate that state-of-the-art VLMs - including large, closed-source models - struggle significantly with structured road reasoning, yet training a small 2- or 4-billion-parameter model with as few as 20 to 80 CRS-enriched scenes yields stable gains in compositional reasoning tasks of varying depth. Analysis of model behavior via verifiable reasoning traces reveals a systematic shift in failure modes: whereas baseline models fail at relational scene understanding, CRS-trained models reduce failures to attribute recognition, suggesting that for structured road reasoning tasks, the lack of structured supervision is a greater limitation than model scale. Project page: https://kth-rpl.github.io/CRS/

cs.CV

新论文 · v1arXiv:2611.23950

VOL-Agent: Programming Your Film via Video Orchestration Language Agentic System

Hongji Yang, Yucheng Zhou, Lingting Zhu, Shengju Qian, Xinye Li, Huan Zheng, Dongyue Lu, Wei Chow 等 11 位作者

原文摘要

Recent video foundation models generate high-quality and limited-length clips, but orchestrating them into minute-level, story-coherent films remains an open problem. Existing video agents highly rely on natural-language planning or predefined workflows, which make their production hard to program, customize, and extend. Therefore, we introduce VOL-Agent, a programmable video agent built on a Video Orchestration Language (VOL). With static compilation and verification, followed by runtime dynamic loading, VOL-Agent decouples structural reliability from execution flexibility. Through the skill-driven executor, VOL-Agent dynamically resolves tools and skills from an open-world repository and supports user-defined skills in natural language. Moreover, VOL-Agent is capable of crafting new director skills from learned knowledge and improves itself through feedback to accumulate filmmaking knowledge. To overcome the disconnect between different segments, we apply a structural memory mechanism to record and recall world and entity states, sustaining entity and scene consistency across different shots. Critic feedback supports local revision, while reusable filmmaking knowledge and experiences can be retained for subsequent tasks. Experiments on three benchmarks show that VOL-Agent generates minute-scale videos with strong overall quality and limited cost.

cs.CV

版本更新 · v2arXiv:2611.01543

GSExplorer: Interactive World Generation with a Persistent 3DGS World State

Sicheng Yu, Liu Liu, Xinjie Wang, Xinjiang Wang, Taojun Ding, Wenhao Hu, Beizhen Zhao, Puxin Yan 等 10 位作者

原文摘要

Interactive world generation requires both accurate local control and stable scene consistency over long rollouts. Existing methods improve local generation through camera or geometry conditioning and extend historical context with memory mechanisms. However, long-horizon exploration remains challenging due to incomplete target-view guidance and inconsistencies accumulated during scene updates. We present \textbf{GSExplorer}, a generation--reconstruction framework built around a persistent 3D Gaussian world state. At each step, the current 3DGS scene provides multimodal rendering conditions for a video generator, while camera geometry is injected through a separate Relative Ray Encoding branch. Generated videos are then fed back to a SLAM-based reconstruction backend, where appearance and geometric consistency checks produce a shared support mask for selective scene updates and cross-chunk pose refinement. We further design a data-construction pipeline that reproduces realistic 3DGS degradation during scene extrapolation, yielding 293K training pairs of degraded multimodal renderings and real target videos. GSExplorer achieves the best overall performance among the compared methods on both single-step and three-step WorldScore evaluation, including a Camera Control score of 99.07 in single-step extrapolation. On 481-frame leave-and-return rollouts, it also shows strong revisit consistency.

cs.CV · cs.AI

版本更新 · v3arXiv:2603.28113

The multiplicative Lipschitz bound as an inductive bias

Simon Kuang, Yuezhu Xu, S. Sivaranjani, Xinfan Lin

原文摘要

We study the problem of training a neural network to minimize a loss function given a Lipschitz constraint. While the most obvious way to estimate the Lipschitz constant of a neural network is to multiply the Lipschitz constants of its layers, this bound, which we term the _trivial bound_, is often considered impractically loose. We show that, on the contrary, it can be more effective than state-of-the-art methods (Sandwich, Almost-Orthogonal Layers, Convex Potential Layers, and SDP-based Lipschitz Layers) for Lipschitz-constrained learning. Our method combines the trivial bound with a novel activation function (the quadrature nonlinearity) to achieve lower cross-entropy over most of the tested classification bounds. For autoencoders constrained to be nonexpansive in a learned norm, it achieves the lowest pixel reconstruction error at every tested bottleneck width, improving on PCA by 12--24%. Our architecture, consisting of concatenated cosine and sine activations, is supported by a semi-rigorous theoretical analysis of Lipschitz bound looseness that may prove valuable in its own right.

cs.LG

新论文 · v1arXiv:2611.23949

Incremental Speciation in Evolutionary Red Teaming of Large Language Models

Onkar Shelar, Travis Desell

原文摘要

Speciation maintains distinct subpopulations in evolutionary search through similarity-based grouping and species-aware parent selection. For text-based individuals, niches depend on both the compatibility representation and the assignment operator that turns pairwise relations into species. We examine this design space in black-box evolutionary red teaming of large language models, comparing embedding and natural language inference (NLI) dissimilarities under representative-based and density-based speciation. Offline calibration on a 3,139-prompt archive shows that MiniLM embedding dissimilarity ($d_E$) and DeBERTa-v3-small NLI non-entailment ($d_{\neg E}$) produce different species structures at the same nominal threshold. Even with pairwise edge density matched to MiniLM, NLI density connectivity forms a few concentrated, mixed-topic species, with substantially more off-topic membership. These structural differences persist online under a matched evaluation budget. The endpoint top-50 median fitness favors incremental DBSCAN over leader-follower, but bootstrap intervals from 10 runs include zero, providing no reliable evidence of an advantage. Semantic diversity among top prompts declines in every configuration, with no consistent method advantage. The clearest difference concerns high-fitness population occupancy: MiniLM incremental DBSCAN maintains mature niches across seed topics, whereas NLI incremental DBSCAN attains the same highest observed median fitness while concentrating high-fitness prompts in variants of a few seed topics. Thus, representation-dependent connectivity predicts population structure more consistently than endpoint fitness. Species count alone does not establish quality-diversity, and more species do not necessarily preserve semantically diverse high-fitness prompts.

cs.NE

新论文 · v1arXiv:2611.23946

How Complete Must an Environment Be to Train a Capable GUI Agent?

Jingxing Wang, Teng Wang, Xingyu Lou, Zihan Guo, Jun Wang, Weiwen Liu, Weinan Zhang, Jianghao Lin

原文摘要

Graphical user interface (GUI) agents are widely trained in executable GUI environments. To lower cost, build environments in batches, and reduce manual effort, each work trades away part of the environment through its construction choices. We describe these choices along three dimensions: reward coverage, the goal-reaching trajectories the verifier rewards; data coverage, the application data the agent is exposed to beyond what the task reads or writes; and feature coverage, the application features beyond what the task uses. Existing works set each dimension on engineering grounds, but they do not measure its effect on training. How complete must an environment be to train a capable agent, and along which dimensions? In MobileGym, we adjust each dimension separately, train Qwen3-VL-4B-Instruct, and evaluate every policy in the original full environment. A verifier that rewards only one reference path lowers success by 10.53 points, and removing unneeded records also lowers success. Pruning unneeded features instead raises success from 51.61% to 56.13%, entirely on tasks whose environments it left unchanged. The gain reverses when each episode is weighted equally and vanishes when only episodes on the pruned tasks are balanced. Without pruning, length weighting there reinforces long detour successes that erode skills on other tasks. Following these findings, we build MobileGym-Lite, which keeps reward and data coverage complete and prunes unneeded features. It outperforms Full in the full environment (55.48% versus 51.61% success) with lower construction cost.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2605.22169

Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning

Vipul Arya, S. H. Shabbeer Basha, Srikrishna U N, Sunainha Vijay, Snehasis Mukherjee

原文摘要

Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on various computer vision tasks such as object classification, detection, segmentation, generation, and more. However, these models are data-hungry as they require more training data to learn millions or billions of parameters. Especially for supervised learning tasks, curating a large number of labeled samples for model training is an expensive and time-consuming task. Active Learning (AL) has been used to address this problem for many years. Existing active learning methods aim to choose the samples for annotation from a pool of unlabeled samples that are either diverse or uncertain. Choosing such samples may hinder the model's performance as we pool based on one dimension, i.e., either diverse or uncertain. In this paper, we propose four novel hybrid sampling methods for pooling both easy and hard samples, which are also diverse. To verify the efficacy of the proposed methods, extensive experiments are conducted using high- and low-confidence samples separately. We observe from our experiments that the proposed hybrid sampling method, Least Confident and Diverse (LCD), consistently performs better than state-of-the-art methods. It is observed that selecting uncertain and diverse instances helps the model learn more distinct features. The code related to this study will be available at https://github.com/vipularya135/LCD.

cs.CV

版本更新 · v2arXiv:2606.29959

Know Before You Fetch: When Does Confidence-Based Retrieval-Budget Allocation Pay Off?

Zhe Dong, Fang Qin, Manish Shah

原文摘要

Adaptive retrieval-augmented generation uses a signal from the reader, such as its confidence when answering without retrieval (closed-book), to decide whether and how much to retrieve. We compare such methods not with always retrieving many passages but with the best simple policy under the same cap on average passages per query: a fixed depth or a random mixture of fixed depths. Policies allocate zero, one or five passages and are scored on held-out questions. Seven settings of about 2,000 questions combine TriviaQA, Natural Questions and MS MARCO, Qwen3-8B and Qwen3-32B readers, and two retrieval sources: per-question passage pools and a 3.5-million-passage Wikipedia index. Allocation by confidence could gain in three ways. It rations a scarce budget: at a cap of half a passage per query it beats the best simple policy in all seven settings, by 0.010 to 0.075 in accuracy. It avoids harmful retrieval: at caps of one passage or more, substantial gains appear only on Wikipedia, where passages often overwrite known answers, most robustly for Qwen3-8B on TriviaQA (+0.051, also under exact match and F1). It barely helps to choose depth: closed-book confidence ranks which queries a first passage helps but ranks the choice between one and five passages little better than chance, and with passage pools a fixed depth of two or three passages is as good or better. Once the probe's latency is charged, gains remain only where the gate skips retrieval for most queries; for the larger reader they also depend on the answer metric.

cs.IR · cs.CL

新论文 · v1arXiv:2611.23944

SIGNTOK: A Text-Aligned Continuous Pose Tokenizer for Sign Language Generation

Nabeela Khan, Gaurav Rai, Bowen Wu, Sihan Tan, Benjamin Yen, Takeshi Ashizawa, Kazuhiro Nakadai

原文摘要

Text-conditioned sign language generation (SLG) depends not only on the generator but also on the space in which signing is generated. Existing approaches generate directly in pose space, in quantized code spaces, or in learned latent spaces trained for reconstruction. We find that these spaces are organized largely by signer identity rather than linguistic content: on CSL-Daily, a test clip's nearest neighbor in raw pose space is the same sentence signed by another person in only 2% of cases. To address this, we propose SIGNTOK, a continuous pose tokenizer whose latent space is shaped by three training-only heads: a kinematics head that predicts motion dynamics, a sentence-level head that aligns signing with the overall text, and a word-level head that aligns short motion windows with content words. Together, these objectives raise the same-sentence cross-signer nearest-neighbor rate to 82%. On three sign language benchmarks, the same generator trained in the SIGNTOK latent instead of pose space raises back-translation BLEU-4 in five of six benchmark-scorer settings at comparable joint accuracy, and word-level alignment gives higher back-translation scores than sentence-level alignment on every benchmark.

cs.CV

新论文 · v1arXiv:2611.23942

GLIDE: Scalable and Event-Aware Inductive Forecasting over Evolving Logistics Graphs

Zhi Sheng, Chuyue Wang, Jiahao Ji, Yile Liang, Xuetao Ding, Jinghua Hao, Jie Feng, Yong Li

原文摘要

Accurate forecasting of order volume at scale-effect hotspots (SEHs), spatially coherent groups of logistics flows that serve as distributed optimization units for real-time many-to-one dispatch, is a prerequisite for efficient order pooling in on-demand food delivery (OFD) platforms such as Meituan. However, real-world logistics networks present unique challenges that render standard spatiotemporal prediction model ineffective. (i) Dynamic Topology: Unlike static road networks, logistics graphs are ephemeral, with hotspot emerging and vanishing continuously; (ii) Scale--Volume Heterogeneity: Graph sizes vary from $10^2$ to $10^4$, while zero-inflated, long-tailed volumes create computational bottlenecks and bias predictions toward inactivity; and (iii) Event-Driven Disruption: Exogenous events (holidays, weather, academic calendars) induce systematic demand shifts that purely data-driven backbones cannot anticipate. In this paper, we present GLIDE, a production-ready framework that models evolving logistics graphs in a scalable latent space while adapting to heterogeneous demand regimes and event-driven shifts. GLIDE introduces a Graph-Guided Latent Aggregation mechanism, which dynamically projects varying physical subgraphs into a fixed-size, semantically stable latent space via a differentiable sparse assignment...

cs.AI

新论文 · v1arXiv:2611.23941

Angular Conditional Distillation: Overcoming Classifier Geometry Mismatch

Xuefei Zhang, Ruoqi Wang, Lei Cui

原文摘要

Classifier outputs provide a fundamental and univer- sally available knowledge interface for knowledge distil- lation (KD). However, standard logit objectives entangle transferable semantic relations with architecture-dependent parameterization artifacts, causing a classifier geometry mismatch that makes direct knowledge transfer unreliable. To address this, we propose Angular Conditional Distilla- tion (ACD). First, the Angular Coordinate Interface (ACI) reconstructs the student classifier using angular coordi- nates, suppressing magnitude and bias effects to provide a geometry-compatible space. Then, Scale-Invariant Condi- tional Distillation (SICD) standardizes outputs and exclu- sively transfers conditional non-target relations, filtering out untransferable absolute confidence. Together, ACI de- fines where to transfer, while SICD defines what to transfer. Extensive experiments show that ACD achieves state-of-the- art performance over existing KD methods. Moreover, as a universal drop-in replacement, it consistently improves existing distillation pipelines while requiring no feature adapters or additional inference-time cost. Code is avail- able at https://github.com/laniusnan/ACD.

cs.CV · cs.AI

新论文 · v1arXiv:2611.23939

Effects of Locomotion and Viewpoint Control on Immersive Robot Telepresence for Navigation and Inspection

Ammaar Zaman, Neven ElSayed, Oliver Prentner, Mohamed Ellethy, Mostafa M. Lotfy, Maram Selsabila Mahmoudi, Eduardo Veas

原文摘要

In many robot telepresence interfaces, movement and viewing are managed through handheld inputs. This can divide attention between steering, looking, and inspection. We compared joystick versus omnidirectional treadmill locomotion and joystick-based versus head-guided camera control in a within-subject 2x2 study in which 17 participants used a virtual reality headset to guide a quadruped robot through a physical maze while locating marked wall symbols and capturing them as visual evidence. Mixed-effects analyses showed that head-guided camera control was associated with faster completion, lower wall-contact cost, lower workload, and more favorable presence, usability, technology acceptance, and flow than joystick-based camera control. The strongest overall objective performance was observed in the joystick locomotion plus head-guided camera condition, whereas the omnidirectional treadmill plus head-guided camera condition emerged as the strongest experiential compromise. Exploratory camera analyses showed that head-guided camera control reduced switching, increased reliance on the pan-tilt view, and supported a more stable viewing strategy across the maze. These strategy differences were consistent with the performance advantage, especially for wall-contact duration. Targets captured remained near ceiling and simulator sickness remained low across all conditions. Overall, the results indicate that viewpoint control was the stronger differentiator in this combined navigation and inspection task, while locomotion still shaped the objective and experiential tradeoff.

cs.RO · cs.HC

新论文 · v1arXiv:2611.23938

Can you make models believe false facts in the prompt?

Ananya Sutradhar, Fabien Roger

原文摘要

Making LLMs believe false facts is useful for alignment evaluations and for building model organisms. Previous work explored doing so with Synthetic Document Finetuning (SDF). But SDF requires fine-tuning one new model for each set of injected false beliefs. To enable larger scale SDF-powered alignment evaluations, we attempt to produce a single model that believes any fact placed in a <facts> tag in the prompt. To do so, we explore doing prompt-conditioned SDF: fine-tuning a model on synthetic documents covering thousands of facts, with each document conditioned on a fact presented in the prompt. We evaluate how deeply the model believes the facts provided in the prompt using evaluations from prior work and a new Jacobian lens evaluation. We find that the belief depth on unseen facts scales roughly log-linearly with the number of training facts, making this a cheap, promising avenue for making models believe false facts, though preliminary experiments on applying it to alignment audits on the small model we studied showed negative results due to these small models often already acting as if they believed facts provided in regular honeypot system prompts. Using RL to reduce the rate at which models verbalize following a false fact in the prompt, on top of prompt-conditioned SDF, generalizes to held-out evals and almost matches SDF on some evaluations. But training against one of our metrics for belief depth makes it harder to trust those evaluations.

cs.AI

新论文 · v1arXiv:2611.23936

PGU-Decoder: Prior-Guided Unified Decoding for Industrial Road-Network Map Updating

Yuguang Ning, Bingbing Kang, Nan Zhao, Zhixuan Li, Ze Zhao, Dongdong Liu, Wenjian Zhu, Zekai Liu 等 9 位作者

原文摘要

Timely road-network map updates are essential to navigation and autonomous driving. Three key tasks are intra-intersection road network generation, merging/diverging detection, and drivable-area detection, covering topology, geometry, and attributes, respectively. Separate pipelines duplicate rule maintenance, quality assurance, and manual verification, increasing operational costs. We propose PGU-Decoder, a production-grade unified decoding framework for semantic prediction across these tasks. A Prior Query Module (PQM) constructs point-level prior queries from sampled locations on road-network geometries. Fixed reference points preserve positional priors throughout decoding, allowing the model to focus on surrounding context. Point-level representations are aggregated into instance-level representations, and a Relational Graph Attention Network (RGAT) captures inter-instance dependencies. Task-specific heads then generate predictions. We validate PGU-Decoder in large-scale automated road-network map updating across more than 360 cities in China, where it consistently outperforms seven baselines. Following deployment at AutoNavi Map, it achieves quality scores above 98% on all three tasks, reduces manual verification costs by 95%, and increases update frequency from weekly to hourly. These results demonstrate a practical and cost-effective industrial solution for road-network map updating.

cs.LG

版本更新 · v3arXiv:2610.16352

LoongSage: A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes

LoongSage Team, Bowei Song, Caiwei Zhao, Chuwen Liu, Dechuang Gu, Dong Fang, Feiyu Xie, Huaiyu Li 等 48 位作者

原文摘要

Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large language models (LLMs). As the frontier of LLM capabilities shifts from static reasoning to agentic tasks--characterized by external tool invocation, multi-turn interactions, and long-horizon decision-making--existing mainstream RL frameworks have grown increasingly unwieldy, raising the overhead of adoption, usage, and debugging. To address these challenges, we present LoongSage, an agent-native, fully asynchronous RL framework with a lightweight core of roughly 14K lines of code. Built upon Megatron for distributed training and SGLang for high-throughput inference, LoongSage centralizes orchestration within a single controller process and encapsulates all GPU-resident components as Ray actors. It introduces AgentFlow, a unified execution paradigm that orchestrates both white-box and black-box agents. For asynchronous execution, it integrates sliding-window strategies that bound trajectory staleness, and employs TransferMesh, a topology-aware synchronization mechanism that routes weights after each step over the fastest transport available to each receiver. Beyond agentic RL, LoongSage incorporates a memory-efficient Teacher Manager that decouples the scaling of teacher models from GPU memory constraints, natively supporting Multi-Teacher On-Policy Distillation. Extensive evaluations across four complete training runs, spanning complex reinforcement learning and multi-teacher distillation, demonstrate that task rewards improve steadily while the train-inference gap is kept under continuous control, and the fully asynchronous pipeline removes synchronous idle bubbles, sustaining hardware utilization.

cs.LG · cs.CL

新论文 · v1arXiv:2611.23935

Facet-SLAM: Real-Time Triangle Splatting SLAM

Edward Beng Wai Tan, Siew-Kei Lam

原文摘要

Dense SLAM systems based on 3D Gaussian splatting build maps that render photorealistically, but their surface geometry is poor, and obtaining a mesh requires extraction or fusion stages. Triangle splatting avoids this with surface primitives whose vertices can be triangulated directly into a connected mesh, yet SLAM with this representation has so far relied on photometric tracking, which is too slow for localization at sensor rate. We present Facet-SLAM, the first real-time triangle splatting SLAM system for RGB-D cameras. Fast geometric registration is the natural alternative, but it is not sufficient alone, since the mapper's optimization displaces triangles from the observed surface and makes them unreliable registration targets. We therefore separate the two roles: the tracker sets each triangle's centroid from fused depth and registers frames to these centroids by GICP, while the mapper is restricted to non-translating updates via a change of variables. Our system achieves competitive tracking accuracy at around 100 FPS on a desktop GPU and runs at sensor rate on a Jetson AGX Orin. Compared with the photometric approach, it is over 20 times faster, matches rendering quality, and improves surface accuracy, reducing the chamfer distance of the Delaunay mesh on Replica from 1.55 to 0.86 cm. We will release the implementation at https://github.com/edward62740/Facet-SLAM.

cs.RO · cs.CV

新论文 · v1arXiv:2611.23934

What Right-Angle Corners Reveal About an Uncalibrated Camera: Convex Cones, Certified Bounds and Identifiability

Michael Werman

原文摘要

The corner of a box or a room, where three perpendicular edges meet, appears in an image as three segments meeting at a point. We ask what such junctions reveal about an uncalibrated camera's intrinsic parameters. Each junction is consistent with an explicit convex set of cameras; when only the focal length is unknown, this set is an interval in closed form. These sets are computed from the image alone, so calibrating from many junctions is a convex feasibility problem. Almost every junction bounds the focal length from below; we characterize when one also bounds it from above, and when many junctions determine it exactly. For a known vertex, the bounds can be certified against any bounded error in the measured edge directions.

cs.CV · math.AG · math.MG

新论文 · v1arXiv:2611.23933

TRoPE: Topology-aware Relative Positional Encoding for 4D Generation

Chengzhuo Gui, Zhenglin Zhou, Fan Ma, Zongxin Yang, Yi Yang

原文摘要

Video-to-4D mesh generation has made substantial progress in recovering dynamic 3D geometry and motion from monocular videos. However, commonly used feed-forward approaches remain prone to sticking artifacts, where geodesically distant vertices move together incorrectly when they become spatially close. We attribute this failure to cross-part motion leakage: spatially nearby yet structurally distant vertices may retrieve similar motion information when motion decoding fails to distinguish spatial proximity from mesh connectivity. To address this issue, we introduce TRoPE, a topology-aware relative positional encoding that makes mesh connectivity explicit in the interaction between vertex queries and mesh-supported motion sources. TRoPE derives spectral features from the graph Laplacian and constructs pairwise topological relations from distances between multi-scale diffusion features, using these relations to modulate vertex--anchor attention through rotary phases. We further introduce a vertex-wise tail-risk objective that emphasizes persistently high-error vertices to explicitly suppress sticking artifacts. To better characterize and quantify these failures, we introduce MeshSticking-4D, a dedicated benchmark for this failure mode. Experiments on MeshSticking-4D show that TRoPE suppresses sticking artifacts while improving overall motion accuracy. Compared with the baseline, it reduces the worst-vertex error by 39.4% and lowers the separation failure rate from 49.35% to 34.90%. Additional evaluations on Motion-80 and Motion324-Subset show lower tail errors on diverse objects, while transfer to Mesh4D demonstrates applicability across backbones.

cs.CV

新论文 · v1arXiv:2611.23932

Emo-H2A: Driving a Facial Robot Directly from LLM Hidden States at Token Rate

Yige Liu, Jingcheng Huang, Hao Sun, Min Li, Zhouping Yin

原文摘要

Diverse, semantically synchronized, and low-latency facial expressions are essential for human-robot interaction. While large language models (LLMs) have endowed anthropomorphic robots with fluent speech, facial expression still struggles to follow the conversation. Motivated by this gap, we present Emo-H2A (hidden-to-actuation), a paradigm that drives a facial robot directly from LLM hidden states during autoregressive decoding. Without a separate emotion label, expression stays continuous and context-sensitive, and the face moves with the unfolding reply. We instantiate this paradigm as EmoManifold, a training-free method that extracts a valence-arousal-dominance (VAD) coordinate from each hidden state, projects it, and drives the face at token granularity. The readout is checked on six language models, and the same projection drives our 29-degree-of-freedom (DoF) facial robot. When driven by this projection, the face shifts its expression in the matching direction on 87.5% of within-reply valence transitions, whereas holding a single label for the whole reply leaves directional tracking near the 50% chance level, and first moves in 0.96s rather than waiting 10-26s for the reply to finish and a turn-level label to return.

cs.RO

版本更新 · v2arXiv:2608.02877

Graph-of-Thoughts for LLM Causal Discovery with a Fairness-Pathway Case Study

Nitish Nagesh, Elahe Khatibi, Thomas Dean Hughes, Mahdi Bagheri, Pratik Gajane, Amir M. Rahmani

原文摘要

Methods that use large language models (LLMs) for causal discovery reason locally, deciding one variable pair or one node at a time, so they never compare alternative whole graphs. We introduce GoT-CD, a Graph-of-Thoughts method that asks an LLM for several complete candidate graphs from variable metadata alone, ranks them with a deterministic validity score, merges them under a hard union constraint, refines the merge, and projects the result to a DAG. We evaluate on Asia, Child, and an Alzheimer's disease graph with 100 samples and GPT-4o-mini. Over five seeds on Alzheimer's and Child, GoT-CD gives the highest mean F1 score and the lowest mean structural Hamming distance of the LLM methods, with 95% intervals of the difference excluding zero in seven of eight comparisons, and it returns a DAG in every run while using three LLM requests per graph. Replaying the logged runs without individual components attributes most of the gain to generating and merging several complete candidates. A case study on the effect of Sex on MOCA Score in the Alzheimer's graph shows the limits of structural scores: the fairness verdict drawn from the discovered graph disagrees with the reference verdict in twelve of fifteen LLM runs, including all five GoT-CD runs, which mostly drop the edge out of Sex. Graphs meant for a specific downstream analysis should therefore also be checked on the pathways that analysis depends on.

cs.LG

版本更新 · v5arXiv:2607.23624

Where Is the Cost of Third-Party API Routers in Agentic Software Development?

Donghao Fu, Jingxin Li, Xue Jiang, Yihong Dong

原文摘要

Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers. In coding-agent workflows, high-autonomy operation is widely adopted because it reduces interaction overhead. As a result, a third-party API router, which sits between the agent and the upstream provider, inevitably occupies the trusted path. It can inspect and modify every request and response, yet no mechanism verifies alignment between the provider's output and the repository-level actions ultimately executed by the agent. Consequently, client-side permission mechanisms may become ineffective in practice. Whether this control gap produces real, hard-to-detect effects on software development tasks remains empirically unmeasured. In this paper, we conduct an empirical study of router-side injection in coding agents, examining four intervention levels of increasing subtlety: Response Substitution (L1), Response Append (L2), LLM-Polished Injection (L3), and LLM-Polished with Distribution Alignment Injection (L4). Moreover, we develop SIDEL, a framework for trace recording, replay, injection, and defense evaluation, with a curated dataset of 400 samples. We evaluate four representative coding agents, and further evaluate whitelist-based execution control and LLM review. Router-side intervention substantially alters repository-level actions and remains difficult for existing client-side safeguards to detect. Without additional mitigations, all evaluated agents achieved a defense success rate of 0 percent across all injection levels. Client-side mitigations and reactive reviews improve resistance but do not fully restore end-to-end control, motivating provider-side output-integrity guarantees. Our code is available at https://github.com/Riyasushin/SIDEL.

cs.SE · cs.AI · cs.CL

新论文 · v1arXiv:2611.23930

A Hierarchical Onboard Vision-Language-Navigation Framework for Aerial Robots in Complex Environments

Yuze Wu, Mo Zhu, Xingxing Li, Yuheng Du, Zhaoqi Wang, Yuxin Fan, Wenjun Li, Kenghou Hoi 等 11 位作者

原文摘要

Unmanned Aerial Vehicles (UAVs) are expected to achieve semantic reasoning, intelligent decision-making, and long-horizon navigation under strict onboard constraints. While recent foundation-model-driven approaches have shown promising progress toward this goal, existing methods remain limited by challenges in 3D data availability, trajectory feasibility, long-horizon reasoning, and computational efficiency in complex environments. To bridge these gaps, we propose VLN-AR, a hierarchical vision-language-navigation (VLN) framework for aerial robots. VLN-AR decouples multimodal reasoning and low-level control, enabling structured prediction of 3D pose commands and navigation intentions that are translated into dynamically feasible actions. To mitigate data scarcity and domain gaps, we introduce a fully automated 3D Gaussian Splatting (3DGS)-based pipeline to generate scalable photorealistic UAV navigation data. A progressive three-stage training strategy further enhances grounding, scene reasoning, and complex navigation. In addition, a lightweight cognitive agent improves long-horizon reasoning via memory-aware task decomposition. Finally, we design onboard optimization techniques, including token sparsification and model lightweighting, achieving 7.1x-9.4x speedup while maintaining high navigation performance on resource-limited UAV platforms. Experiments show great improvements over existing methods in both simulation and real-world UAV navigation. Project website: https://wyz000.github.io/VLN-AR/

cs.RO · cs.AI

版本更新 · v2arXiv:2606.26567

Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework

Yijie Bian, Wei Guo, Jie Yang, Shenghui Song, Jun Zhang, Shi Jin, Khaled B. Letaief

原文摘要

High-frequency massive multiple-input multiple-output (MIMO) systems promise ultra-high data rates. However, efficient beam management remains challenging due to the prohibitive beam training overhead and intricate coordination required in multi-user MIMO (MU-MIMO) scenarios. To address these bottlenecks, environment-aware communications have emerged as a promising paradigm, leveraging site-specific knowledge to circumvent exhaustive pilot-based beam training and streamline multi-user communications. In this paper, we propose a geometry-driven framework that utilizes multi-modal environmental data, specifically regional 3D light detection and ranging (LiDAR) point clouds and location information, to construct an offline virtual base station (VBS) database. By modeling dominant reflection paths via mirror symmetry across building facades reconstructed from the point clouds, the VBS database provides a compact and sparse description of the wireless propagation environment. Given a user location, the VBS representation supports online coarse channel reconstruction and the generation of a beamspace prior. To refine the coarse estimates, we design a VBS-assisted orthogonal-pilot (VOP)-based partial beam training scheme with limited online measurements. Finally, to coordinate beam selection under inter-user interference, we develop a hierarchical dual-agent dueling double deep Q-network for coordinated beam selection (DD3QN-CBS). Simulation results show that the proposed framework improves effective spectral efficiency over the evaluated stochastic, heuristic, and conventional learning-based baselines, while achieving competitive performance with fewer online beam measurements.

eess.SP · cs.AI