MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Paper • 2606.30406 • Published • 19
🔄 In a Training Loop
Pratyay Banerjee
Neilblaze
AI & ML interests
IR, NLP, Pattern Recognition, xAI, Interpretability, Evals
Recent Activity
liked a model 1 day ago
NeuML/biomedbert-hash-nano-embeddings-litert liked a dataset 1 day ago
alessiotoniolo/ART-Chat-2.5MOrganizations
upvoted a paper 3 days ago
upvoted 7
papers 7 days ago
Loop the Loopies!
Paper • 2607.16051 • Published • 74
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
Paper • 2607.18213 • Published • 78
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment
Paper • 2607.07820 • Published • 91
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 103
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
Paper • 2607.11683 • Published • 148
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Paper • 2607.21461 • Published • 151
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Paper • 2607.02512 • Published • 309
upvoted 2
articles 9 days ago
Article
One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker
lightonai
• • 19 Article
Bringing Nunchaku 4-bit Diffusion Inference to Diffusers
rootonchair, sayakpaul
• • 62 upvoted a collection 11 days ago
upvoted an article 14 days ago
Article
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
nvidia
• • 82 upvoted a paper 15 days ago
upvoted 2
articles 16 days ago
Article
Data for Agents
nvidia
• • 26 Article
NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
nvidia
• • 58 upvoted 5
papers 18 days ago
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Paper • 2607.08317 • Published • 35
KronQ: LLM Quantization via Kronecker-Factored Hessian
Paper • 2607.07964 • Published • 32
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Paper • 2607.05147 • Published • 40
TurboServe: Serving Streaming Video Generation Efficiently and Economically
Paper • 2606.19271 • Published • 37
Wan-Streamer v0.2: Higher Resolution, Same Latency
Paper • 2607.04443 • Published • 40