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 08:44 · 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 13:55 — 2026-11-22 13:55(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 08:44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 16 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(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 · v2arXiv:2611.18822

LongCat-Video-Avatar 1.6 Technical Report

Meituan LongCat Team, Xunliang Cai, Yiqi Chen, Feng Gao, Xiaoyu Kong, Le Li, Hongyu Liu, Xiaoming Wei 等 11 位作者

原文摘要

Recent advances in audio-driven avatar video generation have enabled increasingly realistic synthesis, yet achieving precise lip-audio synchronization, natural, human-like motion, and visual consistency over long sequences remains challenging. We present LongCat-Video-Avatar 1.6, which builds on LongCat-Video-Avatar 1.5 to improve expressive naturalness and reduce error accumulation during extended generation, e.g., exaggerated lip movements and overly red, temporally unstable lip coloration, enhance the naturalness of facial expressions and coordinated head and body movements. These improvements are driven by a refined post-training pipeline that integrates reinforcement learning, improved classifier-free guidance strategies for DMD-based few-step distillation, long-video rollouts, and on-policy distillation. Together, these refinements improve expressive realism and enable the generation of videos exceeding 10 minutes while maintaining visual quality and temporal consistency. Arena evaluations show that LongCat-Video-Avatar 1.6 outperforms its predecessor and competing commercial audio-driven avatar models, demonstrating the effectiveness of the improved post-training pipeline.

cs.CV

新论文 · v1arXiv:2611.22206

TAILROLL: Tail-Aware Rollout Acceleration for RL-Based LLM Post-Training

Niloofar Gholipour, Marcos Assuncao, Timothy Yu, Gursimran Singh, Rajkumar Buyya, Julien Gascon-Samson, Zhenan Fan, Yong Zhang

原文摘要

RL post-training of large language models (LLMs) is bottlenecked by rollout: heavy-tailed responses leave engines idle as each step waits for the longest response. Asynchronous training masks, but does not eliminate, idle time. We distinguish imbalance waste (uneven placement and decode contention) from straggler waste (waiting for the longest response). Tail length, not average load, often sets the step bound. We propose TAILROLL, an online scheduler integrated into an open-source RL framework. It combines stateless in-flight migration and sufficiency-gated termination. Migration moves decoding requests between engines at chunk boundaries and resumes them with one re-prefill under a freeness-based, cost-aware tail-balancing policy. Termination stops a response when its GRPO group has enough completed samples for advantage estimation, masking its partial output from the training loss. Across ten configurations, TAILROLL reduces rollout bubble ratio by 21% to 74% and cross-engine KV-cache imbalance by 44% to 79%. In end-to-end RL training, it cuts rollout time by 24% to 34%, full step time by 21% to 22% on long-CoT RL, and p95 request latency by 28% to 37%, while raising generation throughput by up to 33% with comparable or higher final reward.

cs.DC

版本更新 · v3arXiv:2510.23587

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Yizhang Zhu, Liangwei Wang, Chenyu Yang, Xiaotian Lin, Boyan Li, Wei Zhou, Xinyu Liu, Zhangyang Peng 等 25 位作者

原文摘要

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning proactive, generative data agents. A curated companion repository is available at https://github.com/HKUSTDial/awesome-data-agents.

cs.DB · cs.AI

版本更新 · v2arXiv:2611.06704

Where It Breaks: Diagnosing Perception, Memory, and Decision Failures of a Vision-Language Agent in Pac-Man

Xinglu Wang, Edward Wang, Yong Zhang, Zhenan Fan

原文摘要

Spatial agents must interpret observations, maintain consistent spatial memory and make decisions over long interactions. We use Pac-Man as a testbed to study the training challenges behind these capabilities in a Qwen3.5-9B-based agent. Our research trajectory progresses from primitive-action RL on text-based mazes to visual inputs with an internal-state-assisted harness, then toward observation-driven memory and joint policy--harness improvement. The main analysis focuses on text-based maze RL; supplementary sections report visual-adaptation and harness experiments and discuss subsequent directions. Text-based maze RL requires curriculum and training-recipe design to overcome cold starts; normal-start clear rates on eight held-out mazes rise from 0% to a peak of 81.25%. In the second step, model adaptation and harness improvements raise the clear rate from 26.6% to 96.9% on one fixed map with three extra lives. These results highlight three development lessons: use curricula to address cold starts, establish visual grounding before language adaptation, and treat harness design as a determinant of agent performance. They provide practical guidance for subsequent VLM training and spatial-agent development.

cs.LG

新论文 · v1arXiv:2611.15117

PolyMorphWBC: Whole-Body Control from End-Effector Trajectories for Quadrupedal Mobile Manipulation across Arm Morphologies with Extended Reach

Heng Li, Yang Li, Yifan Duan, Ren Fang, Matao Duan, Wenhao Yu, Lu Zhang, Jianmin Ji 等 9 位作者

原文摘要

Quadrupedal mobile manipulators can extend their manipulation workspace by coordinating the mounted arm with the mobile base. At the task level, short-horizon end-effector (EE) trajectories provide an interface for specifying the desired manipulation motion without prescribing how it should be realized by the arm and base. However, executing such trajectories remains challenging because the controller must determine when and how the base should move, and this decision depends on the mounted-arm morphology. We therefore present PolyMorphWBC, a hierarchical controller that takes an EE trajectory as the sole task-level motion command and generates coordinated arm--base motions across four families of 6-DoF mounted arms, with extended-reach trajectories beyond the initial fixed-base reach. Within PolyMorphWBC, a trajectory-conditioned coordinator determines the base motion from previewed EE targets, while arm-specific Inverse Kinematics (IK) tracks the current target, and a frozen locomotion backend executes the resulting motion. Cross-arm reuse is enabled by a Unified Robot Description Format (URDF)-derived morphology conditioning, together with online residual-wrench feedback. We train PolyMorphWBC on procedurally generated arms and structured trajectories within and beyond fixed-base reach. In IsaacLab, it achieves 93.95% completion with 2.30cm position error and 4.81° orientation error on held-out trajectories and arm morphologies. In MuJoCo evaluation against UMI-on-Legs, PolyMorphWBC reduces EE position error by 69--72% and orientation error by 91--97% across four within- and extended-reach trajectories. On a physical Go2--ARX5 system, we demonstrate language-conditioned extended-reach pick-and-place using EE trajectories from pi_0 without vision-language-action (VLA)-generated base commands.

cs.RO

新论文 · v1arXiv:2611.14903

Epigraph Form Reinforcement Learning-based Safe Trajectory Tracking Control for Connected and Autonomous Vehicles

Xiaoke Yang, Jin Chen, Yafei Wang, Qi Zhang, Ming Li, Haiwen Wu, Chengliang Yin, Yong Zhang

原文摘要

Safe trajectory tracking (STT) aims to enable autonomous vehicles to follow a reference trajectory accurately while avoiding collisions. This problem is particularly challenging for Connected and Autonomous Vehicles (CAVs) in highly dynamic environments. Existing non-learning-based STT methods often use simplified vehicle and interaction models to meet real-time requirements, which may result in suboptimal tracking accuracy. Although Deep Reinforcement Learning (DRL) can help address this limitation, widely used Lagrangian DRL methods often suffer from unstable training because increasing Lagrange multipliers amplify policy-gradient magnitudes. To address these issues, we propose a novel reinforcement learning framework for STT, called STT Control Epigraph Form RL (STTC-EFRL). In this framework, the STT problem is formulated as an epigraph-form min-max optimization problem. Based on this formulation, we develop a learning mechanism that uses a decreasing scalar related to the epigraph to adjust the policy gradient descent direction without increasing the gradient magnitude, thereby improving training stability. We also develop a computationally efficient ray-casting method to compute a polyhedron scaling factor for safety quantification. Experimental results, including Vehicle-in-the-Loop tests, show that STTC-EFRL achieves higher tracking accuracy than the considered non-learning-based baseline and more stable training than widely used Lagrangian DRL methods, while satisfying safety requirements in connected environments.

cs.LG

版本更新 · v4arXiv:2505.23277

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression

Yong Zhang, Heng Li, Yanwen Huang, Ning Cheng, Yang Guo, Yun Zhu, Yanmeng Wang, Shaojun Wang 等 9 位作者

原文摘要

Retrieved contexts are often long, noisy, and redundant, motivating query-aware compression before answer generation. Native attention provides signals for context selection, but heterogeneous head behaviors complicate their direct aggregation into sentence-utility scores. We introduce Sentinel, a sentence-level compressor that learns to combine these signals through a signed linear readout across layers and heads. Only the readout is trained using existing QA evidence annotations, while the backbone remains frozen and sentence scoring requires no autoregressive generation. Across twelve LongBench tasks, Sentinel with a 0.5B backbone outperforms Full Context on multiple tasks under a 2,000-token budget with each of three readers: Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, and DeepSeek V4.1 Flash. Despite English-only QA supervision, the same readout transfers to Chinese tasks without task-specific retraining. Length-stratified profiling further shows lower compression latency and GPU memory usage than LLMLingua-2 and CPC.

cs.CL · cs.AI

版本更新 · v3arXiv:2604.09568

EvoDesign:通过设计专长演化实现智能体式可编辑图表创建

EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution

Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan, Zhiyuan Ma, Wei Wu, Yuxuan Lei, Junyang Wang 等 15 位作者

AI 速读 基于摘要

提出一种基于可操作画布中间表示与设计专长演化记忆的智能体框架,用于生成可编辑图表,并给出 CanvasBench 评测基准。

cs.HC · cs.CL · cs.CV

查看原文摘要

High-fidelity diagram creation requires coordinated visual-spatial decisions over semantic topology, visual styling, and geometric layout. Existing methods face a representation gap: pixel-based generation offers limited object-level control, while code-based synthesis provides executable structure at the cost of intuitive manipulation. We introduce EvoDesign, an agentic framework for editable diagram creation through an intermediate canvas schema that is both machine-actionable and directly manipulable by users. EvoDesign first constructs a diagram manifest through coordinated structure, style, and layout agents, and then renders the manifest in a diagnostic verification environment. This environment produces objective defect signals and VLM-based critique, enabling localized refinement of the current diagram while also providing evidence for long-term design expertise evolution. The evolution mechanism distills refinement traces into a three-tier design expertise memory, where candidate strategies are linked to the verification evidence that supports them and are promoted into broader guidelines and principles only through repeated cross-context support. We further define CanvasBench, a canvas-recoverable benchmark and evaluation protocol with content, visual, and cognitive dimensions. Experiments across pixel, code-based, agentic, one-shot schema, and canvas-native methods show that EvoDesign provides the strongest overall balance across content fidelity, visual organization, and cognitive usability. Our code is available at https://github.com/GeminiLight/EvoDesign.

新论文 · v1arXiv:2611.07530

JailBound: FOL-Guided Jailbreak Evaluation for Exploring LLM Behavioral Boundaries

Fazong Wu, Xin Wang, Ming Yang, Zhenyong Zhang, Xiaoming Wu

原文摘要

As large language models (LLMs) are increasingly deployed as general-purpose conversational assistants, they must handle diverse user requests while reliably refusing harmful ones. Jailbreak attacks craft adversarial instructions or conversational contexts to elicit unsafe responses despite these safeguards. However, existing jailbreak benchmarks often rely on manually designed or collected prompts, making it difficult to systematically extend coverage to new threat conditions. Moreover, existing attack search methods typically optimize for attack success rate (ASR), providing limited insight into how model behavior changes locally between safe refusal and unsafe response. To address these limitations, we present JailBound, a unified jailbreak evaluation framework that combines automated benchmark construction with first-order loss (FOL)-guided dual-branch search. JailBound organizes threats by risk category, application domain, and attack type. Conditioned on this taxonomy, a fine-tuned meta-attack generator synthesizes evaluation prompts across diverse threat conditions. FOL serves as a local sensitivity signal for exploring high-value attack states and behavior-sensitive states. We evaluate JailBound across 46 LLMs from 13 model families under a unified experimental protocol. Under matched settings, the High-Value Branch improves average ASR over a ZOL-only baseline by 5.1 and 4.9 percentage points across the two evaluation settings. Under local perturbations, states from the Safety-Sensitivity Branch exhibit higher behavioral flip rates than those from the High-Value Branch across all tested radii for JailBound and S-Eval, indicating greater local sensitivity of judge-assigned safety labels. Warning: this paper includes examples that may be offensive or harmful.

cs.CR

新论文 · v1arXiv:2611.06475

Robocasa-Mem: Benchmarking Environment and Process Memory in Long-Horizon Mobile Manipulation

Sihang Chen, Chen Ye, Wei Chen, Xiaohan Lei, Zhipeng Tang, Sha Zhang, Yuan Zhang, Zixuan Chen 等 11 位作者

原文摘要

In the real world, mobile manipulation robots must perform complex object interactions and make multi-step decisions, often relying on task-relevant information that is no longer observable. However, existing benchmarks provide limited evaluation of such memory-dependent decision-making in mobile manipulation. To address this gap, we introduce RoboCasa-Mem, a new benchmark comprising nine mobile manipulation tasks that require agents to use interaction history at key decision points. Specifically, the tasks are grouped into two categories of memory: One is environment memory, which captures spatial locations, object attributes, and object relationships. The other is process memory, which captures single-task progress and multi-task scheduling. Particularly, we introduce Behavior-Conditioned Evaluation. For tasks with multiple valid execution paths, instead of fixing a single target or trajectory, the evaluator derives later task constraints from the robot's earlier actions. This allows us to evaluate whether later behavior is consistent with the robot's own interaction history while reducing shortcuts based on fixed target assignments. We provide 1,800 successful demonstrations for policy training. We also develop a baseline on our benchmark, namely Hierarchical Memory-Augmented Policy(HMAP). Its high-level planner uses structured entity and process memories to generate subtasks. Its low-level VLA controller uses subgoal-conditioned queries to incorporate VGGT-Omega geometry into action generation. Together, RoboCasa-Mem and HMAP baseline support systematic evaluation of memory-dependent behavior and the development of memory-aware mobile manipulation policies.

cs.RO

新论文 · v1arXiv:2611.06008

Faster Cluster Decomposition with Stronger Bi-Criteria Guarantee

He Sun, Yong Zhang, Yacong Zhou

原文摘要

Partitioning the vertex set of a graph $G=(V,E)$ into clusters is a classical problem in computer science. As vertices within clusters should be well connected and cuts between clusters sparse, Oveis Gharan and Trevisan (SODA 2014, [OGT14]) proposed to measure the partition quality using inner and outer conductance, i.e., the bi-criteria guarantee. Specifically, when partitioning $V$ into vertex-disjoint subsets $P_1,\ldots, P_k$, every subgraph induced by $P_i$ should have high conductance, while the conductance of $P_i$ in $G$ should be low. They studied the existence of such a partition and designed a polynomial-time algorithm achieving this guarantee. For more than a decade, their algorithm remained the only one achieving this guarantee on its output clusters. In this paper, we study faster cluster decomposition algorithms under the same setup as [OGT14] and prove three results: 1. We make their existential result algorithmic: Our algorithms run in nearly-linear time, and achieve the same bi-criteria guarantee as the one in [OGT14] up to constant factors, including the asymptotically tight dependence on $k$. 2. We prove that their existential result holds algorithmically under a much weaker condition on the initial disjoint subsets. To achieve this, we develop a general algorithm framework that boosts the approximation guarantee of a solution: given an $α$-approximate solution to the $k$-way conductance problem, if $ρ_G(k+1)/ρ_G(k)=Ω\left(α/\varepsilon\right)$, then a $(1+\varepsilon)$-approximate solution can be obtained using only $O(k(1+\logα))$ minimum $s$-$t$ cut computations. 3. We present a nearly-linear time algorithm that finds clusters with the bi-criteria guarantee. Our algorithm has the same guarantee as the one in [OGT14], which, for any unweighted graph of $n$ vertices and $m$ edges, runs in $\widetilde{O}(knm^2)$ time.

cs.DS

新论文 · v1arXiv:2611.03294

ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation

Peiyuan Tang, Yao Li, Xiaodong Zhang, Wuyang Zhang, Qin Xia, Yanyong Zhang, Zijiang Yang

原文摘要

Contact-rich manipulation requires fine-grained control and complex physical interactions with the environment, posing significant challenges for robot policy learning. Vision-only policies struggle with such tasks, as contact states and interaction forces are difficult to infer from visual observations alone. Existing methods mitigate this issue by incorporating force or tactile sensing. However, they often treat these signals as auxiliary observations without fully exploiting their role in modeling future interaction dynamics. To address this, we propose ForceLDM, a force-aware latent dynamics model that learns future contact and motion dynamics to guide action generation. Rather than directly predicting future observations, which can entangle task-relevant dynamics with irrelevant sensory details, ForceLDM learns a compact representation of future dynamics through knowledge distillation. Specifically, a teacher network with privileged future force/torque and optical flow signals extracts future dynamic features, which are then distilled into a student network trained only on current observations. This enables the student model to reason about upcoming contacts and physical dynamics without relying on future sensory inputs at deployment. To improve robustness and generalization, we further introduce a curriculum-based progressive noise injection strategy to mitigate over-reliance on future features. Experiments on five real-world contact-rich manipulation tasks demonstrate that ForceLDM outperforms state-of-the-art baselines, generalizes effectively to novel objects, and remains robust to environmental perturbations. Project page and code are available at https://tpy001.github.io/ForceLDM/.

cs.RO

新论文 · v1arXiv:2610.39572

RV2GC: Reconstructing the Garbling Boundary in a RISC-V Garbled Processor

Zixiao Feng, Xiaolin Li, Chenglu Jin, Wei Yan, Yong Zhang, Hongwei Liu, Yong Liu, Qinfen Hao

原文摘要

Programmable garbled-circuit execution must balance the benefits of cross-program reuse against the cost of repeated work during secure execution. A complete garbled processor provides a fixed circuit for many programs, but its evaluator repeatedly visits processor-wide structures even when only a small part performs the current protected computation. We present RV2GC, which reconstructs the garbling boundary around a fixed library of RISC-V instruction circuits. Public scheduling and operand routing operate outside the circuit topologies; persistent label-encoded state connects independently invoked garbled instruction circuits and instruction-specific garbling-free paths through a common interface. A Conditional-execution Stack and protected commits support secret-dependent branches, bounded loops, and secret-indexed memory access under public scheduling, keeping instruction and memory-address sequences independent of private inputs. Across nine benchmarks, measured ARM2GC-to-RV2GC runtime ratios range from 12.81 to 4,043. In terms of circuit size, the largest listed instruction circuit has 3,386 gates, corresponding to 2.044% and 0.393% of the 256-byte and 4,096-byte Amber processors, respectively. Additional comparisons quantify schedule storage, communication, and the cost of secret-dependent execution.

cs.CR · cs.AR

新论文 · v1arXiv:2610.37378

VLA-Stem: A Lightweight Safety Mechanism for Vision-Language-Action Models via Reinforcement Learning

Bojun Zou, Wenhao Yu, Jiaohao Li, Jiaxuan Lin, Guanting Ye, Haohan Geng, Weihao Yu, Yanyong Zhang 等 9 位作者

原文摘要

Vision-Language-Action (VLA) models integrate high-level reasoning with low-level action execution for end-to-end robotic control. However, most VLA models target static manipulation in unconstrained environments, overlooking spatial constraints and dynamic obstacles. Fine-tuning VLAs on obstacle-avoidance data is a straightforward solution, but collecting such data is costly, especially for dynamic scenarios, and may degrade their original task capabilities. To address these limitations, we propose VLA-Stem, a lightweight, reinforcement-learning-based safety mechanism for VLA systems. Without fine-tuning the underlying VLA policy, VLA-Stem converts its action chunks into motion references and uses trajectory-level guidance to preserve their spatial intent while allowing flexible motion and timing adjustments. Conditioned on these references, robot proprioception, and local obstacle information, the Stem policy adaptively modifies execution at inference time, preserving the original task intent while enabling responsive adaptation to spatial constraints and dynamic obstacles. For robust and sample-efficient training, we combine teacher-student distillation with curriculum learning. We evaluate VLA-Stem on reference following, static spatial constraints, and dynamic obstacle avoidance. Across six constrained simulation settings, VLA-Stem achieves 52.8% average collision-free task success versus 23.7% for the strongest safety baseline, while preserving base-policy performance in obstacle-free settings; real-world experiments further show consistent collision reductions under static and dynamic obstacles. These results demonstrate that VLA-Stem couples high-level VLA task intent with rapid, reflex-like responses to immediate physical risks, providing a brainstem-inspired mechanism for robust robot execution.

cs.RO

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1195ACL Anthology · ACL 2026

TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting

Jiaming Leng, Yunying Bi University of Science and Technology of China, Chuan Qin Chinese Academy of Sciences, Zhenya Huang University of Science and Technology of China, Bing Yin iFLYTEK, Haojie Ren, Yanyong Zhang University of Science and Technology of China, Chao Wang University of Science and Technology of China

原文摘要

Urban transportation systems require precise modeling of dynamic spatiotemporal patterns across diverse tasks, such as traffic forecasting, electric vehicle (EV) charging demand prediction, and taxi dispatch. Existing approaches suffer from two key limitations: traditional deep learning models are task-specific and lack generalization capabilities, whereas Large Language Models (LLMs) struggle with structured spatiotemporal data and numerical reasoning. To bridge this gap, we propose TransLLM, a unified multi-task framework that synergizes spatiotemporal encoding with LLM reasoning through learnable prompt composition. To enable LLMs to perceive complex graph dependencies, we design a noise-augmented spatiotemporal encoder that projects structured signals into the LLM’s embedding space. Furthermore, to overcome the rigidity of fixed prompt templates in heterogeneous traffic scenarios, we introduce an instance-level prompt routing mechanism trained via reinforcement learning. The framework operates by encoding spatiotemporal patterns into contextual representations, dynamically composing personalized prompts to guide LLM reasoning, and projecting the resulting representations through specialized output layers to generate task-specific predictions. Experiments on seven datasets and three tasks demonstrate that TransLLM outperforms many baselines, showing superior adaptability in both supervised and zero-shot settings with excellent generalization and robustness. Our code and data are available at https://github.com/lengjiaming/TransLLM.

cs.CL

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