Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
Paper • 2610.06833 • Published • 30
Ayaka Nishimura
ayakani
·
AI & ML interests
anomaly detection
multi-agent RL
reward hacking
Recent Activity
liked a dataset about 16 hours ago
andersonbcdefg/reward-modeling-long-tokenized liked a dataset about 16 hours ago
n1ghtf4l1/Agentic-Diagnostic-Reasoning-with-Multimodal-SLMs-via-Reinforcement-Learning liked a dataset about 16 hours ago
Srishti280992/repro-exact-unlearning-in-reinforcement-learning-tracesOrganizations
None yet
upvoted 4
papers about 16 hours ago
Base Models Can Reason By Taking a Cue From Training Data
Paper • 2610.06851 • Published • 22
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
Paper • 2610.06647 • Published • 121
Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
Paper • 2610.04318 • Published • 18
upvoted 3
papers 1 day ago
LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
Paper • 2609.39071 • Published • 63
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
Paper • 2610.02824 • Published • 32
Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production
Paper • 2609.39963 • Published • 21
upvoted 6
papers 2 days ago
Sharpening Tax in Post-Training
Paper • 2610.01509 • Published • 104
OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning
Paper • 2610.02181 • Published • 21
On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
Paper • 2609.35259 • Published • 198
Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL
Paper • 2610.00574 • Published • 64
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
Paper • 2609.37200 • Published • 138
Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Paper • 2609.36388 • Published • 54
upvoted 7
papers 3 days ago
The Low-Rank Structure of VLA Reinforcement Learning
Paper • 2609.34599 • Published • 21
Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Paper • 2609.39578 • Published • 68
Rubric Rewards from Item Response Theory
Paper • 2609.35646 • Published • 19
TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion
Paper • 2609.38653 • Published • 37
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 581
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
Paper • 2609.38142 • Published • 12
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 293