Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
Paper • 2609.26796 • Published • 14
🔄 In a Training Loop
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
liked a model about 7 hours ago
Qwen/Qwen3-ASR-1.7B-hf liked a model about 7 hours ago
Edge0/ARK-ASR-0.6B liked a model about 8 hours ago
OpenMOSS-Team/MOSS-Transcribe-DiarizeOrganizations
upvoted 9
papers about 17 hours ago
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
Paper • 2609.15991 • Published • 11
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Paper • 2609.22870 • Published • 8
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
Paper • 2609.25804 • Published • 115
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
Paper • 2609.24797 • Published • 7
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Paper • 2609.24983 • Published • 42
Bellman Policy Optimization
Paper • 2609.15987 • Published • 26
LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay
Paper • 2609.25053 • Published • 4
PACT: From Credit Assignment to Critic Alignment
Paper • 2609.26355 • Published • 14
upvoted 2
papers 1 day ago
upvoted 4
papers 3 days ago
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Paper • 2609.05571 • Published • 113
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Paper • 2609.22068 • Published • 130
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
Paper • 2609.15126 • Published • 12
Calibrating Teacher--Student Discrepancy for On-Policy Distillation
Paper • 2609.21619 • Published • 13
upvoted 3
papers 5 days ago
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Paper • 2609.19499 • Published • 37
Verifiable Social Reasoning for LLM Assistants
Paper • 2609.17496 • Published • 62
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Paper • 2609.20715 • Published • 42
upvoted 2
papers 6 days ago