When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 110
Richard Wilson
Rapid-Richard
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 14 days ago
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation liked a model 17 days ago
unsloth/Qwen3.8-27B-GGUF upvoted a paper 19 days ago
Atria Dawn: The Dawn of Agentic SuperintelligenceOrganizations
None yet
upvoted a paper 14 days ago
upvoted a paper 19 days ago
upvoted a paper 24 days ago
upvoted 2
papers 25 days ago
upvoted a paper 30 days ago
upvoted 6
papers about 2 months ago
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
Paper • 2608.17426 • Published • 161
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
Paper • 2608.14391 • Published • 287
PixSDS: Why Latent SDS Makes Noisy Pixels
Paper • 2608.12997 • Published • 11
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Paper • 2608.00677 • Published • 266
MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
Paper • 2607.27637 • Published • 7
World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation
Paper • 2608.05369 • Published • 27
upvoted 3
papers 2 months ago
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
Paper • 2608.03812 • Published • 29
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
Paper • 2608.02023 • Published • 161
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
Paper • 2607.28617 • Published • 37