← authors · overview

• MemFly: On-the-Fly Memory Optimization via Information Bottleneck
  2026
• Self-Evolving Deep Research via Joint Generation and Evaluation
  2026
• Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation
  2026
• Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
  2026
• QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
  2026
• ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
  2026
• TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
  2026
• Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test
  2026
• Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection
  2026
• InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents
  2025
• Can World Models Benefit VLMs for World Dynamics?
  2025
• WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation