Task Interference in VLMs for Autonomous Driving: When Better Perception Hurts Planning.

Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning.

LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval.

Next-Frame Prediction as a Reliability-Aware Training Paradigm for Robust Vision Encoders.

Future Is Unevenly Distributed: Forecasting Ability Of LLMs Depends On What We’re Asking.

Beyond Hallucinations: A Composite Score for Measuring Reliability in Open-Source Large Language Models.

Quantifying Conversational Reliability of Large Language Models under Multi-Turn Interaction.

AlignVQA: Debate-Driven Multi-Agent Calibration for Vision Language Models.

Can In-Context Learning Defend against Backdoor Attacks to LLMs.

VISOR: Visual Input based Steering for Output Redirection in Large Vision Language Models.

Beyond Grey-Box Assumptions: Uncertainty-Guided Example Selection for Black-Box Language Models.

Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models.

Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models.

SafeGen: Benchmarking Inference-Time Methods for Privacy-Preserving Text Generation.

BLUFF-1000: Measuring Uncertainty Expression in RAG.

Reasoning Models are Test Exploiters: Rethinking Multiple Choice.

Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis.

Know Or Not: a library for systematically evaluating out-of-knowledge base robustness.

Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls.

Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles.

Prompt-Adaptive Quantization: Adaptive Per-Prompt Routing for Efficient LLM Inference.

BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision Language Models.

COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation.