Tomas Novak

t-novak's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 2 hours ago

S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning

Paper • 2610.35518 • Published 3 days ago • 33

Nested Sparsity for Scalable Pretraining and Continual Learning

Paper • 2610.31818 • Published 7 days ago • 14

upvoted 2 papers 1 day ago

Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs

Paper • 2610.27103 • Published 10 days ago • 41

Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

Paper • 2610.14465 • Published 12 days ago • 9

upvoted a paper 2 days ago

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 7 days ago • 259

upvoted 3 papers 4 days ago

SpatialBrain: Spatial Intelligence Growing from Experience

Paper • 2610.29317 • Published 8 days ago • 20

Orbia: Do Generated Videos Form a Consistent 3D World?

Paper • 2610.20693 • Published 15 days ago • 50

Qwen-Audio-3.1-ASR Technical Report

Paper • 2610.28711 • Published 9 days ago • 37

upvoted 2 papers 5 days ago

TraceForge: Distilling with Your Own Thinking

Paper • 2610.29680 • Published 8 days ago • 50

AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics

Paper • 2610.28589 • Published 9 days ago • 49

upvoted a paper 7 days ago

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published 14 days ago • 38

upvoted a paper 9 days ago

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Paper • 2610.19366 • Published 15 days ago • 56

upvoted a paper 10 days ago

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

Paper • 2610.17552 • Published 16 days ago • 38

upvoted a paper 11 days ago

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

Paper • 2602.05758 • Published 17 days ago • 24

upvoted a paper 14 days ago

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Paper • 2609.33304 • Published Sep 27 • 26

upvoted a paper 16 days ago

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published about 1 month ago • 157

upvoted a paper 18 days ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published 23 days ago • 111

upvoted 2 papers 19 days ago

Learning Functional Subspaces for Neural Network Compression

Paper • 2609.40127 • Published 29 days ago • 26

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Paper • 2610.07832 • Published 23 days ago • 13

upvoted a paper 20 days ago

ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context

Paper • 2609.36684 • Published about 1 month ago • 20