Trajectory-Aware Hidden-State Analyses

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 32

All topics

TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks
Sep 30, 2026Yiming Gao, Shaocheng LuoTwo-Dimensional Light Detection And Ranging Autonomous Driving Perception
Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA. · Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA.
Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework
Sep 30, 2026Yaohua Liu, Yifan Guo, Jiaxin GaoAdversarial Training Bilevel Optimization
The University of Hong Kong Hong Kong, China · International School of Information Science & Engineering Dalian University of Technology, Dalian, China · The Hong Kong Polytechnic University Hong Kong, China
On Trajectory-Aware Training for Masked Diffusion Language Models
Sep 29, 2026Manuel Madeira, Amitis Shidani, Alice Bizeul +6Masked Diffusion Language Models Diffusion Models
EPFL · Apple · Georgia Institute of Technology
TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
Sep 29, 2026Yalun Wu, Bingzhou Wang, Boyang Wang +5Visual Evidence Multimodal Retrieval Augmented Generation
NExT++ Lab, National University of Singapore
Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies
Sep 28, 2026Jeongsol Kim, Youngjun Jun, Kyumin Choi +6Flow-Matching Vision-Language-Action Critic-Free Reinforcement Learning
KAIST · SKKU · GIST
Accelerating Video Diffusion via Training-Free Trajectory Routing
Sep 24, 2026Mustafa Munir, Huy Vu, Shreyas Misra +7Video Diffusion Models Denoising Trajectory
From Collaboration to Capability: Internalizing Routed LLM Experts into Compact Reasoners
Sep 14, 2026Frank Nie, Shuyao Wang, Ethan B. LiuRecursive Reasoner Experts
Shandong University · Zhejiang University
TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization
Aug 30, 2026Shiliang XiaoJailbreak Attacks Jailbreaks
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
Aug 16, 2026Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu +1Jailbreak Attacks Trajectory-Aware Hidden-State Analyses
Texas A&M University · Amazon
TAPAS: Throughput-adaptive Perception for Autonomous Systems
Jul 19, 2026Aman Vyas, Vasista Kodumagulla, Zain Taufique +2Perception Trajectory-Aware Hidden-State Analyses
Department of Computing, University of Turku, Finland
TVTA: Trajectory-Aware Viseme-Guided Temporal Aggregation for Event-Based Lip Reading
Jul 9, 2026Jingrong Zheng, Hongwei Ren, Xiangqian WuTrajectory-Aware Hidden-State Analyses
Harbin Institute of Technology, China
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training
Jul 6, 2026Qiuyi Qi, Tian Liang, Mutian Bao +8Agentic Reinforcement Learning Trajectory-Aware Hidden-State Analyses
Zhejiang University · Ant Group · City University of Hong Kong
Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution
Jun 18, 2026Mingyu Yang, Keye Zheng, Congchao Cheng +4Probe-Logit Distillation Trajectory-Aware Hidden-State Analyses
Alibaba International Digital Commerce Group
TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation
Jun 13, 2026Tri-Nhan Vo, Dang Nguyen, Sunil GuptaDownstream Reasoning Trajectory-Aware Hidden-State Analyses
Deakin Applied AI Initiative, Deakin University, Australia
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents
Jun 6, 2026Tanush Swaminathan, Runmin Jiang, Letian Zhang +1Scientific Agents Scientific Workflows
Carnegie Mellon University · Allen Institute
LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts
Jun 6, 2026Maxx Richard Rahman, Prakhar Kumar, Wolfgang MaassMultimodal Clinical Data Missing Modalities
German Research Centre for Artificial Intelligence (DFKI) Saarbrücken, Germany
Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models
Jun 3, 2026Anant Khandelwal, Manish GuptaLarge Language Model Reinforcement Learning Diffusion Language Models
Microsoft AI, India
Trajectory-Aware Node Contributions and the Limits of Static Controllability
Jun 2, 2026Valentina Kuskova, Dmitry Zaytsev, Michael CoppedgeNonlinear Dynamics Controllability
Lucy Family Institute for Data & Society · University of Notre Dame · Notre Dame, IN, USA +1
Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes
May 29, 2026Ibne Farabi Shihab, Sanjeda Akter, Anuj SharmaMarkov Decision Processes Topology
Department of Computer Science, Iowa State University · Department of Civil, Construction & Environmental Engineering, Iowa State University
Trajectory-Aware Best-Arm Identification for Local Search Allocation in Bayesian Optimization and Beyond
May 29, 2026Nobuo Namura, Sho TakemoriBayesian Optimization Trust Region
Fujitsu Limited, Kawasaki, Japan.
Bridging the Sampling Distribution Shift in Radio Map Estimation: A Trajectory-Aware Paradigm
May 27, 2026Feng Qiu, Zheng Fang, Shuhang Zhang +4Radio Map Estimation Unmanned Aerial Vehicle Trajectories
School of Artificial Intelligence, Xidian University, Xian, China · Pengcheng Laboratory, China · Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China +2
Molecular Lead Optimization via Agentic Tool Planning
May 21, 2026Lingxiao Li, Haobo Zhang, Ruohao Fan +2Molecular Optimization Drug Discovery
University of Michigan Ann Arbor, Michigan, USA · Department of Biochemistry and Molecular Medicine University of California, Davis Davis, California, USA · Department of Pharmacology and Toxicology Michigan State University East Lansing, Michigan, USA
MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
May 21, 2026Amir Mousavi, Mohammad Sadegh Sirjani, Erfan Nourbakhsh +5Eye Tracking Cognitive Load
Department of Computer Science, College of AI, Cyber and Computing, The University of Texas at San Antonio · Department of Neuroscience, Developmental and Regenerative Biology, College of Sciences, The University of Texas at San Antonio · Department of Educational Psychology, College of Education and Human Development, The University of Texas at San Antonio
Manifold-Guided Attention Steering
May 20, 2026Ian Li, Kapilesh Guruprasad, Raunak Sengupta +3Linear Activation Steering LLM Reasoning Strategies
University of California, San Diego
Accelerating Rectified Flow Models via Trajectory-Aware Caching
May 16, 2026Xiao Liu, Kai Liu, Naiyang Guan +5Rectified Flow Denoising Trajectory
Shanghai Jiao Tong University, Shanghai, China · Academy of Military Science, Beijing, China · Huawei Technologies Ltd, Shenzhen, China
EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
May 13, 2026Hengwei Ye, Jiasheng Mao, Zhenhan Guan +1Agentic Search Agentic Crawlers
ShanghaiTech University
Before the Last Token: Diagnosing Final-Token Safety Probe Failures
May 12, 2026Shravan DodaJailbreak Attacks Prompt-Injection Detectors
Kipo AI
Trajectory-Aware Adaptive Inference in Object Detection Models
May 12, 2026Grigorios Papanikolaou, Ioannis Kontopoulos, Giannis Spiliopoulos +2Ship Detection Object Detection
Department of Electrical and Computer Engineering, National Technical University of Athens, Greece · Department of Product and Systems Design Engineering, University of the Aegean, Syros, Greece
Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability
May 11, 2026Harsh Raj, Niranjan Orkat, Suvrorup Mukherjee +3Agentic Evaluations Trustworthy Artificial Intelligence
Northeastern University · University of P´ecs · University of Michigan +2
Breaking the Communication-Accuracy Trade-off: A Sparsified Information Diffusion Framework for Multi-Agent Collaborative Perception
May 1, 2026Jirong Zha, Chenyu Zhao, Nan Zhou +5Collaborative Perception Trajectory-Aware Hidden-State Analyses
Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China · Shenzhen Institute of Artificial Intelligence and Robotics, Shenzhen, China, 518000 · Shenzhen Smart City Technology Development Group, Shenzhen, China, 518000
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
Mar 21, 2026Hyomin Lee, Sangwoo Park, Yumin Choi +3Attacker Large Language Model Red-Teaming
KAIST · University of California, Los Angeles
Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning
Sep 26, 2025Li Xia, Jing Yu, Zheng Liu +3Federated Learning Diffusion Inversion
Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, 100081, China

Sep 30, 2026, cs.ROJ/K move · Enter open · S save

TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks

Yiming Gao, Shaocheng Luo

Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA. · Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA.

Two-Dimensional Light Detection And Ranging Autonomous Driving Perception Tactics Scene Reasoning Trajectory-Aware Hidden-State Analyses Large Language Model Planning+2

Open paper AskPDF arXiv

Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding traffic. We present TACTIC, a scene-aware framework that uses a multimodal large language model (MLLM) to coordinate state-adaptive roadside LiDAR attacks. Under a gray-box threat model, TACTIC relies only on an attacker-operated roadside perception stack, without accessing the victim LiDAR's native point clouds or internal processing. Local perception provides metric vehicle states, while the MLLM combines these measurements with roadside imagery to infer relational traffic context and construct a semantic scene graph. Based on this representation, TACTIC selects and configures two complementary primitives: \emph{push-away}, which shifts the perceived range of a lead vehicle, and \emph{phantom-obstacle braking}, which triggers emergency braking through obstacle injection. Measured traffic states and empirically calibrated constraints ground the generated tactics in physically feasible operating regions. To accommodate MLLM latency, TACTIC overlaps reasoning and execution asynchronously while high-rate local perception detects scene changes and triggers replanning. Across 280 randomized CARLA trials, the full policy achieves a 100% collision rate, compared with 35% for a fixed rule, 60% for random selection, and 75% for a restricted LLM using mode selection with default parameters. Joint physical-and-image input achieves 100% success, versus 65% with physical measurements alone and 75% with imagery alone, while asynchronous

Δ

refresh reduces scene-mutation response from 7.4 s to 2.0 s. These results show that scene-dependent tactical planning can expose context-sensitive LiDAR failure modes that fixed attack policies may miss.

Momentum

Related topics

Latest papers 32