Tomas Novak

t-novak's activity

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

upvoted a paper about 19 hours ago

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

Paper • 2610.17552 • Published 7 days ago • 45

upvoted a paper 2 days ago

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

Paper • 2602.05758 • Published 8 days ago • 27

upvoted a paper 5 days ago

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

Paper • 2609.33304 • Published 23 days ago • 48

upvoted a paper 7 days ago

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

Paper • 2609.38169 • Published 21 days ago • 135

upvoted a paper 8 days ago

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

Paper • 2610.08448 • Published 14 days ago • 213

upvoted a paper 9 days ago

Learning Functional Subspaces for Neural Network Compression

Paper • 2609.40127 • Published 20 days ago • 25

upvoted a paper 10 days ago

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Paper • 2610.07832 • Published 14 days ago • 13

upvoted a paper 11 days ago

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

Paper • 2609.36684 • Published 21 days ago • 20

upvoted a paper 12 days ago

HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents

Paper • 2610.03574 • Published 18 days ago • 60

upvoted a paper 13 days ago

E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models

Paper • 2609.37533 • Published 21 days ago • 67

upvoted a paper 14 days ago

Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans

Paper • 2606.10953 • Published 20 days ago • 60

upvoted a paper 15 days ago

Rufus-Air: An Open LLM Post-Training Recipe

Paper • 2609.29421 • Published 26 days ago • 44

upvoted a paper 16 days ago

CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments

Paper • 2609.38087 • Published 21 days ago • 25

upvoted a paper 17 days ago

APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants

Paper • 2609.37559 • Published 21 days ago • 47

upvoted 2 papers 18 days ago

An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning

Paper • 2609.35505 • Published 22 days ago • 32

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Paper • 2609.33781 • Published 23 days ago • 46

upvoted a paper 19 days ago

LastOPD: Taming Collapse in Latent On-Policy Distillation

Paper • 2609.28845 • Published 27 days ago • 31

upvoted a paper 20 days ago

FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance

Paper • 2609.25716 • Published 28 days ago • 24

upvoted a paper 21 days ago

Hunyuan-A13B Technical Report

Paper • 2609.27284 • Published 27 days ago • 24

upvoted a paper 22 days ago

Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models

Paper • 2609.24657 • Published 29 days ago • 40