Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2410.02343v2 Announce Type: replace Abstract: Large language models (LLMs) routinely fail to output the correct option in multiple-choice question answering (MCQA) while encoding the answer int...
arXiv:2601.19918v2 Announce Type: replace Abstract: Hallucinations in Large Language Models (LLMs), i.e., plausible but non-factual generations, pose a significant challenge to reliable deployment in...
arXiv:2609.38476v1 Announce Type: new Abstract: Synthetic data are most valuable where general-purpose datasets cannot provide the domain-specific priors a task requires, and where manual annotation...
The paper introduces Stackelberg Alignment, a leader‑follower framework that lets a pool of language models collaborate and improve by learning from each other’s responses. An EXP3 bandit leader adaptively selects instructions based on difficulty and discriminability, while the models act as followers, evaluating peers and learning via DPO or GRPO with Elo‑style reputation weighting and opponent matching. Experiments on diverse benchmarks show that this adaptive curriculum outperforms static baselines by up to 12‑25% and improves multi‑LLM evolution.
arXiv:2609.38839v1 Announce Type: new Abstract: Long-horizon video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retainin...
arXiv:2609.38913v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains vulnerable to domain shifts from illumination, motion, and...
arXiv:2609.39134v1 Announce Type: new Abstract: Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study a...
arXiv:2609.39266v1 Announce Type: new Abstract: Fine-grained vision-language alignment in chest radiography enables zero-shot classification, grounding, and segmentation without task-specific annotat...
arXiv:2609.39366v1 Announce Type: new Abstract: Remote sensing object counting estimates how many buildings, vehicles, or ships appear in overhead images. Most supervised counters predict a density m...
arXiv:2609.39486v1 Announce Type: new Abstract: Estimating accident mechanics from real-world crashes is important for vehicle-safety analysis, injury modeling, crash-severity prediction, and operati...
arXiv:2609.40244v1 Announce Type: new Abstract: Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving effi...
arXiv:2609.38494v1 Announce Type: cross Abstract: Robotic manipulation integrates vision, touch, and language, whose importance shifts across stages: vision guides reaching, while touch, through its...
arXiv:2601.08355v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for sa...
arXiv:2602.02914v4 Announce Type: replace Abstract: Privacy-preserving face recognition (PPFR) and face anonymization have different goals, but both must retain some identity-related information for...
arXiv:2603.17343v3 Announce Type: replace Abstract: The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Tradition...
arXiv:2603.18792v3 Announce Type: replace Abstract: Uncertainty quantification (UQ) is crucial in safety-critical applications such as medical image segmentation. Total uncertainty is typically decom...
arXiv:2603.24528v2 Announce Type: replace Abstract: Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that...
arXiv:2605.12649v3 Announce Type: replace Abstract: Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and...
arXiv:2607.03470v2 Announce Type: replace Abstract: Synthesizing physically accurate mirror reflections remains a fundamental challenge for modern text-to-image diffusion models, which are increasing...
arXiv:2609.32740v2 Announce Type: replace Abstract: Intraoperative anesthesia requires systems to interpret evolving multimodal evidence, recommend timely management, and revise decisions as patient...