Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models Paper • 2605.27243 • Published May 26
Neurosymbolic Reasoning Shortcuts under the Independence Assumption Paper • 2507.11357 • Published Jul 15, 2025
Do Composed Image Retrieval Benchmarks Require Multimodal Composition? Paper • 2605.14787 • Published May 15
Do Composed Image Retrieval Benchmarks Require Multimodal Composition? Paper • 2605.14787 • Published May 15
Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge Paper • 1808.08609 • Published Aug 26, 2018
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions Paper • 2106.01798 • Published Oct 27, 2021
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language Paper • 1906.06187 • Published Jun 14, 2019
Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations Paper • 1910.03065 • Published May 2, 2020
Learning Reasoning Strategies in End-to-End Differentiable Proving Paper • 2007.06477 • Published Aug 24, 2020
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Paper • 2607.01002 • Published 5 days ago • 15
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Paper • 2607.01002 • Published 5 days ago • 15
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Paper • 2607.01002 • Published 5 days ago • 15
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models Paper • 2603.06148 • Published Mar 6 • 2
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks Paper • 2605.31433 • Published May 29 • 28
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks Paper • 2605.31433 • Published May 29 • 28
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks Paper • 2605.31433 • Published May 29 • 28