It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them
Paper • 2609.37863 • Published • 39
Tomer Keren
tomer-keren
AI & ML interests
None yet
Recent Activity
liked a Space 3 months ago
EilamSha/glee-competition-leaderboard upvoted a paper 3 months ago
From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMsOrganizations
None yet
upvoted a paper 19 days ago
upvoted a paper 3 months ago
upvoted 4
papers 4 months ago
Selective Safety Steering via Value-Filtered Decoding
Paper • 2605.14746 • Published • 4
Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning
Paper • 2604.18419 • Published • 3
Beyond IID: How General Are Tabular Foundation Models, Really?
Paper • 2606.30410 • Published • 42
LLM Explainability with Counterfactual Chains and Causal Graphs
Paper • 2606.05972 • Published • 19
upvoted 3
papers 5 months ago
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
Paper • 2605.28556 • Published • 75
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
Paper • 2605.12411 • Published • 49
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Paper • 2605.10616 • Published • 143