Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models Paper • 2604.06912 • Published 7 days ago • 7
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens Paper • 2604.04913 • Published 9 days ago • 8
Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment Paper • 2604.05684 • Published 8 days ago • 7
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning Paper • 2604.05846 • Published 8 days ago • 9
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs Paper • 2604.05643 • Published 8 days ago • 12
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization Paper • 2604.07343 • Published 7 days ago • 12
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Paper • 2604.07340 • Published 7 days ago • 15
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents Paper • 2604.04247 • Published 10 days ago • 29
MARS: Enabling Autoregressive Models Multi-Token Generation Paper • 2604.07023 • Published 7 days ago • 36
Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism Paper • 2604.09544 • Published 5 days ago • 4
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents Paper • 2603.27490 • Published 17 days ago • 14
FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios Paper • 2604.07413 • Published 7 days ago • 85
ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models Paper • 2604.08064 • Published 6 days ago • 7
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference Paper • 2604.07394 • Published 7 days ago • 15
Structured Distillation of Web Agent Capabilities Enables Generalization Paper • 2604.07776 • Published 6 days ago • 19
OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence Paper • 2604.07296 • Published 7 days ago • 35