{"total":54,"rows":[{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"area":"safety"},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2505.18949","title":"The Price of Format: Diversity Collapse in LLMs","created":"2025-05-25","cited_by_count":43,"area":null},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42,"area":"lr"},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2503.07523","title":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","created":"2025-03-10","cited_by_count":39,"area":"lr"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2406.11801","title":"Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations","created":"2024-06-17","cited_by_count":32,"area":"alignment"},{"id":"2503.15621","title":"LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning","created":"2025-03-19","cited_by_count":28,"area":"mllm"},{"id":"2505.23854","title":"Revisiting Uncertainty Estimation and Calibration of Large Language Models","created":"2025-05-29","cited_by_count":23,"area":"moe"},{"id":"2505.15000","title":"Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems","created":"2025-05-21","cited_by_count":12,"area":"lr"},{"id":"2510.17489","title":"DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning","created":"2025-10-20","cited_by_count":12,"area":null},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2506.06211","title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","created":"2025-06-06","cited_by_count":8,"area":"lr"},{"id":"2505.16703","title":"Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs","created":"2025-05-22","cited_by_count":7,"area":"mllm"},{"id":"2506.02921","title":"A Controllable Examination for Long-Context Language Models","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2507.06323","title":"Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms","created":"2025-07-08","cited_by_count":7,"area":"agents"},{"id":"2601.20026","title":"Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","cited_by_count":6,"area":"lr"},{"id":"2509.00388","title":"GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction","created":"2025-08-30","cited_by_count":6,"area":"inference"},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2602.16958","title":"Automating Agent Hijacking via Structural Template Injection","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2509.07941","title":"ImportSnare: Directed \"Code Manual\" Hijacking in Retrieval-Augmented Code Generation","created":"2025-09-09","cited_by_count":5,"area":"rag"},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2502.16147","title":"Number Representations in LLMs: A Computational Parallel to Human Perception","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2505.24244","title":"Mamba Knockout for Unraveling Factual Information Flow","created":"2025-05-30","cited_by_count":4,"area":"ssm"},{"id":"2507.22337","title":"A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2510.08238","title":"Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness","created":"2025-10-09","cited_by_count":4,"area":"agents"},{"id":"2409.01688","title":"Differentially Private Kernel Density Estimation","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2501.09444","title":"Solving the Unsolvable: Translating Case Law in Hong Kong","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2506.00495","title":"FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2509.20639","title":"A Framework for Rapidly Developing and Deploying Protection Against Large Language Model Attacks","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"id":"2605.01205","title":"SRA: Span Representation Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":3,"area":"alignment"},{"id":"2509.24943","title":"Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents","created":"2025-09-29","cited_by_count":2,"area":"agents"},{"id":"2510.13982","title":"Static Sandboxes Are Inadequate: Modeling Societal Complexity Requires Open-Ended Co-Evolution in LLM-Based Multi-Agent Simulations","created":"2025-10-15","cited_by_count":2,"area":"agents"},{"id":"2511.09385","title":"AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment","created":"2025-11-12","cited_by_count":2,"area":"alignment"},{"id":"2603.19466","title":"ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models","created":"2026-03-19","cited_by_count":2,"area":"mllm"},{"id":"2501.17391","title":"LFTR: Learning-Free Token Reduction for Multimodal Large Language Models","created":"2025-01-29","cited_by_count":1,"area":"mllm"},{"id":"2507.09016","title":"Enhancing RLHF with Human Gaze Modeling","created":"2025-07-11","cited_by_count":1,"area":"alignment"},{"id":"2507.20749","title":"Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study","created":"2025-07-28","cited_by_count":1,"area":"mllm"},{"id":"2508.07308","title":"HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways","created":"2025-08-10","cited_by_count":1,"area":"lr"},{"id":"2511.00509","title":"Reimagining Safety Alignment with An Image","created":"2025-11-01","cited_by_count":1,"area":"alignment"},{"id":"2511.07441","title":"AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents","created":"2025-11-03","cited_by_count":1,"area":"agents"},{"id":"2601.05588","title":"Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2403.18205","title":"Exploring the Privacy Protection Capabilities of Chinese Large Language Models","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2503.16893","title":"Improving the End-to-End Efficiency of Offline Inference for Multi-LLM Applications Based on Sampling and Simulation","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2503.17963","title":"Won: Establishing Best Practices for Korean Financial NLP","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2509.12459","title":"Does Language Model Understand Language?","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2509.16965","title":"Preference Distillation via Value based Reinforcement Learning","created":"2025-09-21","cited_by_count":0,"area":"alignment"},{"id":"2606.12479","title":"ReCal: Reward Calibration for RL-based LLM Routing","created":"2026-06-10","cited_by_count":0,"area":"lr"}],"next_cursor":null}