TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward
Paper • 2607.21606 • Published • 1
Yury Panikov
panikov
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward upvoted a paper about 9 hours ago
Characterizing Warp Divergence from Pascal to BlackwellOrganizations
None yet
upvoted 20
papers about 9 hours ago
Characterizing Warp Divergence from Pascal to Blackwell
Paper • 2607.23402 • Published • 2
Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features
Paper • 2607.23370 • Published • 2
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Paper • 2607.23909 • Published • 4
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs
Paper • 2607.22639 • Published • 3
A Vocabulary for Multi-Agent Automated Research Systems
Paper • 2607.22682 • Published • 3
Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models
Paper • 2607.21936 • Published • 9
A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever
Paper • 2607.23806 • Published • 4
Codifying the Judge: Scalable Evaluation via Program Distillation
Paper • 2607.22561 • Published • 6
Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models
Paper • 2607.22098 • Published • 6
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
Paper • 2607.24743 • Published • 7
dRAE: Representation Autoencoder with Hyper-Spherical Codes
Paper • 2607.22148 • Published • 9
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Paper • 2607.24720 • Published • 22
Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On
Paper • 2607.21694 • Published • 24
Data Pyramid for Embodied Manipulation
Paper • 2607.24744 • Published • 32
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
Paper • 2607.22798 • Published • 55
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Paper • 2607.24731 • Published • 68
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Paper • 2607.24280 • Published • 73
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey
Paper • 2607.21655 • Published • 113
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
Paper • 2607.23588 • Published • 113