Riya Krishnamurthy

riyakir's activity

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

upvoted 3 papers 2 days ago

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Paper • 2610.01892 • Published 11 days ago • 36

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

Paper • 2610.07767 • Published 6 days ago • 93

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

Paper • 2610.07043 • Published 7 days ago • 44

upvoted 3 papers 3 days ago

Base Models Can Reason By Taking a Cue From Training Data

Paper • 2610.06851 • Published 7 days ago • 25

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Paper • 2610.06647 • Published 7 days ago • 148

Towards Looped Models Done Right, Part II: Rethinking at Fixed Points

Paper • 2610.06833 • Published 7 days ago • 33

upvoted 3 papers 4 days ago

MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning

Paper • 2610.02824 • Published 10 days ago • 33

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

Paper • 2609.39071 • Published 12 days ago • 66

Tail-Influence Sampling for CVaR Policy Evaluation

Paper • 2609.38096 • Published 13 days ago • 28

upvoted 5 papers 5 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 11 days ago • 111

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization

Paper • 2609.32993 • Published 16 days ago • 79

Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL

Paper • 2610.00574 • Published 12 days ago • 65

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 14 days ago • 202

InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation

Paper • 2610.02196 • Published 11 days ago • 62

upvoted 3 papers 6 days ago

Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

Paper • 2609.39578 • Published 12 days ago • 72

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 13 days ago • 553

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published 12 days ago • 274

upvoted 3 papers 7 days ago

Diffusion Reward Models

Paper • 2609.33803 • Published 15 days ago • 35

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published 14 days ago • 180

LLMs are General Asynchronous Agents

Paper • 2609.35427 • Published 14 days ago • 86