Yuxin Ma

yuxinmaster's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 2 hours ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published 5 days ago • 195

upvoted a paper 1 day ago

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published 5 days ago • 88

upvoted a paper 2 days ago

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

Paper • 2610.05162 • Published 7 days ago • 60

upvoted a paper 3 days ago

On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training

Paper • 2609.36659 • Published 12 days ago • 87

upvoted a paper 4 days ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 12 days ago • 140

upvoted a paper 5 days ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 11 days ago • 506

upvoted a paper 6 days ago

Context Language Models

Paper • 2609.37725 • Published 12 days ago • 46

upvoted a paper 7 days ago

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 13 days ago • 394

upvoted a paper 8 days ago

WorldAttention: An Efficient Attention Architecture for Interactive Video World Models

Paper • 2609.34606 • Published 13 days ago • 50

upvoted a paper 9 days ago

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

Paper • 2609.33757 • Published 14 days ago • 234

upvoted a paper 10 days ago

Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks

Paper • 2609.22237 • Published Sep 3 • 10

upvoted a paper 11 days ago

RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation

Paper • 2609.29028 • Published 17 days ago • 16

upvoted 7 papers 12 days ago

Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery

Paper • 2609.27980 • Published 18 days ago • 6

Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI

Paper • 2609.24815 • Published 18 days ago • 12

On the Diffusibility of High-Dimensional Latents

Paper • 2609.28473 • Published 18 days ago • 19

MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

Paper • 2609.28256 • Published 18 days ago • 17

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 479

InternW0: A Foundational Physical World Model for Efficient Real-World Interactions

Paper • 2609.27656 • Published 18 days ago • 15

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling

Paper • 2609.22947 • Published 22 days ago • 43

upvoted a paper 13 days ago

Embedding Physics Priors in Robot Learning: A Survey

Paper • 2609.22319 • Published 26 days ago • 19