ROSS: Relearning from Self-Generated Rollouts through Selective Supervision
Paper • 2609.35954 • Published • 46
Finn Reyes
finnreyes
AI & ML interests
Retrieval-augmented generation, dense retrieval, open-domain question answering, RAG pipelines
Recent Activity
upvoted a paper about 15 hours ago
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision upvoted a paper about 15 hours ago
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding? upvoted a paper about 15 hours ago
Adversarial Training for Pixel DiffusionOrganizations
None yet
upvoted 7
papers about 15 hours ago
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?
Paper • 2609.38079 • Published • 52
Adversarial Training for Pixel Diffusion
Paper • 2609.38170 • Published • 20
Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
Paper • 2609.33781 • Published • 43
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
Paper • 2609.27334 • Published • 55
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
Paper • 2609.36322 • Published • 106
In-Context Learning for Robots: Methods and Applications
Paper • 2609.36012 • Published • 379
upvoted 7
papers 1 day ago
Omni-IO Skills: Harnessing Your Agent Omni-Native
Paper • 2609.31847 • Published • 286
Follow the Entities: A Corpus Map for Agentic Search
Paper • 2609.37226 • Published • 93
Reasoning with Image Generation
Paper • 2609.16409 • Published • 21
Chinese-Jev: Bringing System One Model to Chinese-Language Tasks
Paper • 2609.36965 • Published • 22
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Paper • 2609.33439 • Published • 550
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Paper • 2609.37868 • Published • 58
Scheduling Recursive Reasoning in Looped Transformers
Paper • 2609.36653 • Published • 16
upvoted a paper 3 days ago
liked a
model 4 days ago
upvoted 4
papers 4 days ago
Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure
Paper • 2609.23551 • Published • 7
D-JEPA: A Decision-Aligned Latent World Model
Paper • 2609.24749 • Published • 17
Disaggregated Quantization: Specializing LLM Prefill and Decode
Paper • 2609.26333 • Published • 91
TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
Paper • 2609.27277 • Published • 32