Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation
Paper • 2610.36466 • Published • 31
🔄 In a Training Loop
Joel Wang
joelhenwang
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
Quat3rnion/Signal-3.8-Flash-Next-HGN-v2-abliteratedOrganizations
upvoted 17
papers 4 days ago
AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark
Paper • 2610.31466 • Published • 19
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents
Paper • 2610.26233 • Published • 28
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
Paper • 2610.30755 • Published • 32
Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
Paper • 2610.25100 • Published • 55
Speculative Diffusion is a Tale of Two Tradeoffs
Paper • 2610.31819 • Published • 29
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
Paper • 2610.32770 • Published • 48
RSIHub: A Composable Framework for Agent-Evolution Methods
Paper • 2610.32253 • Published • 50
Skill^{infty}: Recursive Self-Improvement for Agent Skill Optimization
Paper • 2610.35434 • Published • 9
Beyond Benchmarks: Can Small Open-Weight Models Get Real Coding Work Done?
Paper • 2610.34241 • Published • 10
How Far Can Coding Agents Go in Visual Generation?
Paper • 2610.19025 • Published • 32
Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
Paper • 2610.33845 • Published • 32
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
Paper • 2610.33024 • Published • 30
On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
Paper • 2610.22543 • Published • 54
The Lexical Imprint of Pre-training Data
Paper • 2602.10657 • Published • 12
What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
Paper • 2610.34491 • Published • 38
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Paper • 2610.32046 • Published • 29
upvoted 3
papers 11 days ago
SpatialBrain: Spatial Intelligence Growing from Experience
Paper • 2610.29317 • Published • 14
Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation
Paper • 2610.30128 • Published • 31
Harness Scaling for Generalizable Agentic Reinforcement Learning
Paper • 2610.29458 • Published • 24