Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Paper • 2610.02967 • Published • 41
Finn Reyes
finnreyes
AI & ML interests
combinatorial optimization, test-time compute
Recent Activity
upvoted a paper about 21 hours ago
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards upvoted a paper about 21 hours ago
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation upvoted a paper about 21 hours ago
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed ExpertsOrganizations
None yet
upvoted 5
papers about 21 hours ago
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
Paper • 2610.12442 • Published • 40
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
Paper • 2610.12448 • Published • 11
REMORY: Learning Residual Memory for Context Compaction
Paper • 2610.11287 • Published • 59
SparseEngine: Sparse-First Inference Engine
Paper • 2609.39068 • Published • 22
upvoted 6
papers 1 day ago
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers
Paper • 2610.11816 • Published • 15
Foundations of Large Language Models
Paper • 2501.09223 • Published • 51
SuperNav: An Agentic Navigation System for Any Task in Any Scene
Paper • 2610.12126 • Published • 86
What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
Paper • 2610.06406 • Published • 26
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
Paper • 2610.12402 • Published • 14
V-CoLA: Vision Token Compression with Linear Attention
Paper • 2610.11251 • Published • 15
upvoted 5
papers 3 days ago
UNREAL: Unifying Retrieval and Long-Context with a Single Model
Paper • 2610.08463 • Published • 31
World Models' Last Exam in Physics
Paper • 2610.08791 • Published • 30
Sherpa: Teaching LLMs to Teach Adaptively
Paper • 2610.08778 • Published • 15
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Paper • 2610.08430 • Published • 27
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
Paper • 2610.00864 • Published • 49
upvoted 4
papers 4 days ago
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces
Paper • 2609.40362 • Published • 40
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 97
SearchJev: A Fast and Calibrated System-1 Model for Search Agents
Paper • 2610.05107 • Published • 26
Personal-Agent Mediated Recommendation with Cross-Platform User History
Paper • 2610.07588 • Published • 12