Hao Chen
8 papers · Latest:
RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
RecRM-Bench introduces a comprehensive benchmark for multi-dimensional reward modeling in LLM-agent recommender systems, addressing current limitations.
HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
HarmoWAM unifies predictive and reactive control in robot manipulation, achieving both generalizable transit and precise interaction through adaptive expert coordination.
MARBLE: Multi-Aspect Reward Balance for Diffusion RL
MARBLE introduces a gradient-space optimization framework to balance multiple rewards for diffusion RL, improving all dimensions simultaneously without manual weighting.
LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models
LaST-R1 enhances VLA models with adaptive latent physical reasoning and a new RL algorithm, LAPO, achieving near-perfect robotic manipulation.
PrismaDV: Automated Task-Aware Data Unit Test Generation
PrismaDV is an AI system that generates task-aware data unit tests by analyzing downstream code and dataset profiles, improving data reliability.
Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
This paper investigates critical factors in 3D visual geometry estimation, revealing insights and introducing CARVE, a resolution-enhanced model for robust performance.
MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation
MMControl enables fine-grained multi-modal control for synchronized joint audio-video generation using a dual-stream diffusion transformer.
Atomic-scale origin of charge density wave-driven metal-semiconductor transition in an incommensurately modulated metal-organic framework
This paper reveals the atomic-scale origin of a charge density wave-driven metal-semiconductor transition in a metal-organic framework.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.