REMORY: Learning Residual Memory for Context Compaction
Paper • 2610.11287 • Published • 59
Li Xiaohao
xiaohaonlp
AI & ML interests
Multimodal Learning
Recent Activity
upvoted a paper 1 day ago
REMORY: Learning Residual Memory for Context Compaction upvoted a paper 1 day ago
Multi-Agent Egocentric World Model with Fine-Grained Embodied InteractionOrganizations
None yet
upvoted 10
papers 1 day ago
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
Paper • 2609.38173 • Published • 64
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Paper • 2610.12299 • Published • 68
SuperNav: An Agentic Navigation System for Any Task in Any Scene
Paper • 2610.12126 • Published • 86
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Paper • 2610.11959 • Published • 90
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Paper • 2610.06100 • Published • 141
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Paper • 2610.12242 • Published • 140
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 154
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 287
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
Paper • 2610.18206 • Published • 10
upvoted 8
papers 5 months ago
VISTA: A Test-Time Self-Improving Video Generation Agent
Paper • 2510.15831 • Published • 24
A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency
Paper • 2605.06924 • Published • 17
Heterogeneous Scientific Foundation Model Collaboration
Paper • 2604.27351 • Published • 175
Let ViT Speak: Generative Language-Image Pre-training
Paper • 2605.00809 • Published • 33
Hallucinations Undermine Trust; Metacognition is a Way Forward
Paper • 2605.01428 • Published • 24
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 359
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 156
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Paper • 2605.03849 • Published • 129