58 citations · 120 across the 59 of their papers we have counts for
18 papers · 1 filter
Expert Merging in Sparse Mixture of Experts with Nash Bargaining
Dung V. Nguyen, Anh T. Nguyen, Minh H. Nguyen +6
Existing expert merging strategies for Sparse Mixture of Experts (SMoE) typically rely on input-dependent or input-independent averaging of expert parameters, but often lack a prin…
Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image
Sapir Esther Yiflach, Yuval Atzmon, Gal Chechik
Text-to-image diffusion models can generate stunning visuals, yet they often fail at tasks children find trivial--like placing a dog to the right of a teddy bear rather than to the…
Per-Query Visual Concept Learning
Ori Malca, Dvir Samuel, Gal Chechik
Visual concept learning, also known as Text-to-image personalization, is the process of teaching new concepts to a pretrained model. This has numerous applications from product pla…
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion
Anum Afzal, Florian Matthes, Gal Chechik +1
We investigate whether the success of a zero-shot Chain-of-Thought (CoT) process can be predicted before completion. We discover that a probing classifier, based on LLM representat…
Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning
Zhengyi Luo, Chen Tessler, Toru Lin +8
Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements…
Policy Optimized Text-to-Image Pipeline Design
Uri Gadot, Rinon Gal, Yftah Ziser +2
Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even…
MaskedManipulator: Versatile Whole-Body Manipulation
Chen Tessler, Yifeng Jiang, Erwin Coumans +3
We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion t…
Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
Vignesh Balaji, Christos Kozyrakis, Gal Chechik +1
Graph Neural Networks (GNNs) enable learning on realworld graphs and mini-batch training has emerged as the de facto standard for training GNNs because it can scale to very large g…
Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms
Ido Greenberg, Piotr Sielski, Hugo Linsenmaier +5
Vehicle Routing Problems (VRP) are an extension of the Traveling Salesperson Problem and are a fundamental NP-hard challenge in combinatorial optimization. Solving VRP in real-time…
Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds
Eitan Shaar, Ariel Shaulov, Gal Chechik +1
In the domain of audio-visual event perception, which focuses on the temporal localization and classification of events across distinct modalities (audio and visual), existing appr…
TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features
Dana Cohen-Bar, Daniel Cohen-Or, Gal Chechik +1
As 3D content creation continues to grow, transferring semantic textures between 3D meshes remains a significant challenge in computer graphics. While recent methods leverage text-…
Single Image Iterative Subject-driven Generation and Editing
Yair Shpitzer, Gal Chechik, Idan Schwartz
Personalizing image generation and editing is particularly challenging when we only have a few images of the subject, or even a single image. A common approach to personalization i…
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
Michael Toker, Ido Galil, Hadas Orgad +4
Text-to-image (T2I) diffusion models rely on encoded prompts to guide the image generation process. Typically, these prompts are extended to a fixed length by adding padding tokens…
OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models
Dvir Samuel, Matan Levy, Nir Darshan +2
In Omnimatte, one aims to decompose a given video into semantically meaningful layers, including the background and individual objects along with their associated effects, such as…
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
Guy Bar-Shalom, Fabrizio Frasca, Derek Lim +5
The automated detection of hallucinations and training data contamination is pivotal to the safe deployment of Large Language Models (LLMs). These tasks are particularly challengin…
Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization
Aviv Shamsian, Eitan Shaar, Aviv Navon +2
Machine unlearning aims to remove the influence of problematic training data after a model has been trained. The primary challenge in machine unlearning is ensuring that the proces…
Classifier-Guided Captioning Across Modalities
Ariel Shaulov, Tal Shaharabany, Eitan Shaar +2
Most current captioning systems use language models trained on data from specific settings, such as image-based captioning via Amazon Mechanical Turk, limiting their ability to gen…
RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
Uri Gadot, Assaf Shocher, Shie Mannor +2
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an o…