activity
20192026
most citedBeyond Performance: Quantifying and Mitigating Label Bias in LLMs

1 citations · 1 across the 6 of their papers we have counts for

collaborators

12 papers

cs.CV2026

On the Adversarial Robustness of Discrete Image Tokenizers

Rishika Bhagwatkar, Irina Rish, Nicolas Flammarion +1

Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-dec…

cs.LG2026

On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks

Yannic Neuhaus, Nicolas Flammarion, Matthias Hein +1

Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of re…

cs.AI2026

HalluHard: A Hard Multi-Turn Hallucination Benchmark

Dongyang Fan, Sebastien Delsad, Nicolas Flammarion +1

Large language models (LLMs) still produce plausible-sounding but ungrounded factual claims, a problem that worsens in multi-turn dialogue as context grows and early errors cascade…

cs.LG2025

Selective Induction Heads: How Transformers Select Causal Structures In Context

Francesco D'Angelo, Francesco Croce, Nicolas Flammarion

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, at…

cs.SE2025

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Thomas Kuntz, Agatha Duzan, Hao Zhao +4

Computer use agents are LLM-based agents that can directly interact with a graphical user interface, by processing screenshots or accessibility trees. While these systems are gaini…

cs.CV2025

Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning

Sara Ghazanfari, Francesco Croce, Nicolas Flammarion +3

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve the…