Kunal Srinivasan

kunalsrini's activity

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

upvoted 2 papers about 4 hours ago

Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps

Paper • 2610.02740 • Published 14 days ago • 10

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published 16 days ago • 298

upvoted 5 papers 1 day ago

Rethinking Relative Policy Differences Transfer of On-Policy Distillation

Paper • 2610.13205 • Published 7 days ago • 16

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Paper • 2610.12341 • Published 8 days ago • 46

Reflex: Visually Grounded Reactive Humanoid Control

Paper • 2610.12772 • Published 8 days ago • 151

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

Paper • 2610.12572 • Published 8 days ago • 316

S-Space: Exploring Spatial Workspace in Multimodal Language Models

Paper • 2610.13527 • Published 6 days ago • 292

upvoted 3 papers 3 days ago

On KL-Regularized Policy Optimization

Paper • 2610.08963 • Published 10 days ago • 26

SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

Paper • 2610.09832 • Published 9 days ago • 14

Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

Paper • 2610.08621 • Published 10 days ago • 95

upvoted 4 papers 5 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 15 days ago • 111

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

Paper • 2609.35259 • Published 18 days ago • 204

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

Paper • 2609.39578 • Published 16 days ago • 72

RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning

Paper • 2610.09455 • Published 9 days ago • 46

upvoted 3 papers 6 days ago

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

Paper • 2610.07767 • Published 10 days ago • 93

NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale

Paper • 2610.08430 • Published 10 days ago • 27

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

Paper • 2610.07043 • Published 11 days ago • 47

upvoted 3 papers 7 days ago

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

Paper • 2610.06647 • Published 11 days ago • 152

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

Paper • 2610.06833 • Published 11 days ago • 34

Base Models Can Reason By Taking a Cue From Training Data

Paper • 2610.06851 • Published 11 days ago • 28