Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
Paper • 2608.20281 • Published • 13
Patricia Thompson
Patricia-Thompson
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 13 days ago
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation upvoted a paper 13 days ago
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RLOrganizations
None yet
upvoted a paper 11 days ago
upvoted 2
papers 13 days ago
upvoted 3
papers 16 days ago
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 • 281
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 170
CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers
Paper • 2608.12773 • Published • 9
upvoted 3
papers 20 days ago
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Paper • 2608.05604 • Published • 80
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Paper • 2608.00677 • Published • 263
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
Paper • 2608.08814 • Published • 10
upvoted a paper 21 days ago
upvoted a paper 25 days ago
upvoted a paper 26 days ago
upvoted a paper 27 days ago
upvoted a paper 29 days ago