Technion Israel institute of technology · 14 records

dateidtitleauthorsvenue↑
2026-11-202611.26073AltRA-Test: An Alternative Annotator Test for LLM Judges Without Shared AnnotatorsNagham Omar et al.arXiv20
2026-11-192611.17600LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular LearningEilam Shapira et al.arXiv22
2026-11-022610.42136ReLift: Dense 3D Tracking as Lifted Trajectory RepairAssaf Singer et al.arXiv26
2026-10-162610.18125H-DDCM: Hadamard Codebooks for Fast Generative Image and Video CompressionOr Ronai et al.arXiv4
2026-10-022610.01428Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMsNagham Omar et al.arXiv7
2026-10-012609.39841DyRAD: Radar Novel View Synthesis for Dynamic Driving ScenesMerav Keidar et al.arXiv28
2026-10-012609.37863It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing ThemNagham Omar et al.arXiv20
2026-09-102609.06806Train Smarter, Not Harder: Switching Signal-Guided Training in Active LearningNagham Omar et al.arXiv5
2026-06-192606.20404FlowBender: Feedback-Aware Training for Self-Correcting Conditional FlowsDaniel Gilo et al.arXiv21
2026-06-112606.07881Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight InconsistencyItay Elam et al.arXiv6
2026-06-082606.05972LLM Explainability with Counterfactual Chains and Causal GraphsNirit Nussbaum-Hoffer et al.arXiv19
2026-06-022605.28556A Matter of TASTE: Improving Coverage and Difficulty of Agent BenchmarksTomer Keren et al.arXiv73
2026-05-142605.10616MulTaBench: Benchmarking Multimodal Tabular Learning with Text and ImageAlan Arazi et al.arXiv142
2026-05-142605.12411Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular ModelingEilam Shapira et al.arXiv48