Senthil Kumar N

Senthi1Kumar's activity

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

upvoted a paper about 9 hours ago

On-Policy Self-Distillation in Diffusion Models

Paper • 2608.24646 • Published 2 days ago • 48

upvoted a paper about 18 hours ago

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 3 days ago • 182

upvoted a paper 1 day ago

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

Paper • 2608.21360 • Published 6 days ago • 28

upvoted 3 papers 4 days ago

Towards Quantifying Benchmark Optimization in ASR Models

Paper • 2608.19936 • Published 7 days ago • 11

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Paper • 2608.19799 • Published 7 days ago • 63

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 7 days ago • 263

upvoted a paper 9 days ago

Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence

Paper • 2608.11341 • Published 16 days ago • 64

upvoted 11 papers 24 days ago

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Paper • 2607.26057 • Published about 1 month ago • 33

Voice Memory for Agentic Speech Recognition

Paper • 2607.26410 • Published 29 days ago • 11

Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

Paper • 2607.27372 • Published 29 days ago • 19

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published 28 days ago • 44

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

Paper • 2606.30406 • Published Jun 29 • 25

Recursive Harness Self-Improvement

Paper • 2607.15524 • Published Jul 17 • 26

MemHarness: Memory Is Reconstructed, Not Replayed

Paper • 2607.28272 • Published 28 days ago • 17

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Paper • 2607.26497 • Published 28 days ago • 51

PhiZero: A World Model Built Around Physical Language

Paper • 2607.28624 • Published 28 days ago • 170

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published 28 days ago • 185

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 28 days ago • 309

upvoted 2 papers 26 days ago

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

Paper • 2605.09530 • Published May 10 • 150

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 29 days ago • 272