Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals
Research
Research News
New papers, breakthroughs and academic AI research
CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Research
Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize
Research
Self-conditioned Flow Map Language Models via Fixed-point Flows
Research
One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
Research
Moore, Escher, Penrose: A Conformal Golden Braid
Research
DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation
Research
SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding
Research
Sphere Encoder 2
Research
Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
Research
MMMG: a Comprehensive and Reliable Benchmark for Multitask Multimodal Generation
Research
Retrospective Open-Vocabulary Memory for Long-Term Object Search
Research