相关论文: Gaslight, Gatekeep, V1-V3: Early Visual Cortex Ali…

AI alignment refers to models acting towards human-intended goals, preferences, or ethical principles. Given that most large-scale deep learning models act as black boxes and cannot be manually controlled, analyzing the similarity between…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts…

Vision-language models (VLMs) show promise as tools for inferring affect from visual stimuli at scale; it is not yet clear how closely their outputs align with human affective ratings. We benchmarked nine VLMs, ranging from state-of-the-art…

Sycophantic response patterns in Large Language Models (LLMs) have been increasingly claimed in the literature. We review methodological challenges in measuring LLM sycophancy and identify five core operationalizations. Despite sycophancy…

Spatial relations are a basic part of human cognition. However, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and-language models (VLMs) struggle to capture relational…

Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…

Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI benchmarks, including EQA, typically rely on static…

For state-of-the-art image understanding, Vision Transformers (ViTs) have become the standard architecture but their processing diverges substantially from human attentional characteristics. We investigate whether this cognitive gap can be…

Modern visual world modeling systems increasingly rely on high-capacity architectures and large-scale data to produce plausible motion, yet they often fail to preserve underlying 3D geometry or physically consistent camera dynamics. A key…

Vision-Language Models (VLMs) have shown remarkable progress in visual understanding in recent years. Yet, they still lag behind human capabilities in specific visual tasks such as counting or relational reasoning. To understand the…

The increasing integration of Large Language Models (LLMs) into decision-making frameworks has exposed significant vulnerabilities to social compliance, specifically sycophancy and conformity. However, a critical research gap exists…

Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes…

Recent advancements in vision-language models have achieved remarkable results in making language models understand vision inputs. However, a unified approach to align these models across diverse tasks such as image captioning and visual…

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key…

The alignment of vision-language representations endows current Vision-Language Models (VLMs) with strong multi-modal reasoning capabilities. However, the interpretability of the alignment component remains uninvestigated due to the…

Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in…

Understanding what individual neurons encode is a core question in neuroscience. In primary visual cortex (V1), mathematical models (e.g., Gabor functions) capture neural selectivity, but no comparable framework exists for higher areas. We…

Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-answering (VQA) datasets may overfit dataset-specific biases, while integrating specialized…