On-Policy Self-Distillation in Diffusion Models
Paper • 2608.24646 • Published • 67
🔄 In a Training Loop
Pratyay Banerjee
Neilblaze
AI & ML interests
IR, NLP, Pattern Recognition, xAI, Interpretability, Evals
Recent Activity
liked a Space about 22 hours ago
jasperai/t2i-technical-interactive-report liked a model 1 day ago
MirroS-Lab/Code-as-World-VL-9B liked a model 1 day ago
QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4Organizations
upvoted 8
papers 7 days ago
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 48
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
Paper • 2608.04205 • Published • 53
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Paper • 2608.21156 • Published • 63
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
Paper • 2608.27260 • Published • 72
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Paper • 2608.16157 • Published • 107
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
Paper • 2608.06867 • Published • 111
EnvHarness: Awakening Static Worlds for Agent Learning
Paper • 2608.19880 • Published • 274
upvoted 5
articles 14 days ago
Article
Making Knowledge Distillation Cheap Enough to Run at Scale
MultiverseComputingCAI
• • 40 Article
How Much Memory Does Your Agent Actually Need?
ibm-research
• • 76 Article
Up to 3.2x Faster Inference with LFM2.5-DSpark
LiquidAI
• • 51 Article
Multimodal Embedding & Reranker Models with Sentence Transformers
tomaarsen
• • 72 Article
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
- +1
tomaarsen, NohTow, raphaelsty
• • 106 upvoted 7
papers 16 days ago
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
Paper • 2608.14277 • Published • 35
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Paper • 2608.06301 • Published • 35
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
Paper • 2608.05013 • Published • 37
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Paper • 2608.19197 • Published • 52
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Paper • 2608.06197 • Published • 47
Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
Paper • 2608.07169 • Published • 50
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Paper • 2608.13417 • Published • 58