Gal Chechik

Latest

• Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms
• Policy Optimized Text-to-Image Pipeline Design
• RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
• From Glucose Patterns to Health Outcomes: A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis
• MaskedManipulator: Versatile Whole-Body Control for Loco-Manipulation
• OmnimatteZero: Training-free Real-time Omnimatte with Pre-trained Video Diffusion Models
• Motion by Queries: Identity-Motion Trade-offs in Text-to-Video Generation
• IT^3: Idempotent Test-Time Training
• Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
• Policy Gradient via Tree Expansion
• RL-Initialized Genetic Algorithms for Faster Vehicle Routing
• TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features
• Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds
• Make It Count: Text-to-Image Generation with an Accurate Number of Objects
• Real-Time Rate Control for Task-Aware Video Compression Using Reinforcement Learning
• Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
• Analyzing Large Language Models by Learning on Token Distribution Sequences
• ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation
• From Glucose Patterns to Health Outcomes (Workshop): A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis
• Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
• Classifier-Guided Captioning Across Modalities
• Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
• MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting
• Equivariant Deep Weight Space Alignment
• Improved Generalization of Weight Space Networks via Augmentationss
• Train Hard, Fight Easy: Robust Meta Reinforcement Learning
• SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
• Norm-guided latent space exploration for text-to-image generation
• Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
• Equivariant Architectures for Learning in Deep Weight Spaces
• Graph Positional Encoding via Random Feature Propagation
• Learning to Initiate and Reason in Event-Driven Cascading Processes
• Point-Cloud Completion with Pretrained Text-to-image Diffusion Models
• Key-Locked Rank One Editing for Text-to-Image Personalization
• CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
• Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
• Planning and Learning with Adaptive Lookahead
• Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
• Multi-Task Learning as a Bargaining Game
• Optimizing Tensor Network Contraction Using Reinforcement Learning
• An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
• Reinforcement Learning with a Terminator
• "This is my unicorn, Fluffy": Personalizing frozen vision-language representations
• Reinforcement Learning for Datacenter Congestion Control
• Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction
• StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
• From Local Structures to Size Generalization in Graph Neural Networks
• How to Stop Epidemics: Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
• Compositional Video Synthesis with Action Graphs
• GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
• Known unknowns: Learning novel concepts using exploratory reasoning-by-elimination
• Personalized Federated Learning using Hypernetworks
• A causal view of compositional zero-shot recognition
• Auxiliary Learning by Implicit Differentiation
• Learning the Pareto Front with Hypernetworks
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• On Learning Sets of Symmetric Elements