相关论文: Decoupling Perception from Reasoning for Hallucina…

Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models for various…

Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present DROPOUT DECODING, a novel inference-time approach that…

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel…

Reinforcement learning with verifiable rewards (RLVR) has shown great potential to enhance the reasoning ability of large language models (LLMs). However, due to the limited amount of information provided during the RLVR process, the model…

Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new scenarios remains expensive due to large-scale retraining and costly mean opinion score…

Hallucinations in Large Language Models (LLMs) pose a major barrier to their reliable use in critical decision-making. Although existing hallucination detection methods have improved accuracy, they still struggle with disentangling semantic…

Object hallucination has been an Achilles' heel which hinders the broader applications of large vision-language models (LVLMs). Object hallucination refers to the phenomenon that the LVLMs claim non-existent objects in the image. To…

Aligning large language models (LLMs) to accurately detect hallucinations remains a significant challenge due to the sophisticated nature of hallucinated text. Recognizing that hallucinated samples typically exhibit higher deceptive quality…

Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on…

We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, SeViLA, or GPT-4). Compared to existing benchmarks that focus on…

Video understanding has achieved great success in representation learning, such as video caption, video object grounding, and video descriptive question-answer. However, current methods still struggle on video reasoning, including evidence…

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…

Large Vision-Language Models (LVLMs) have obtained impressive performance in visual content understanding and multi-modal reasoning. Unfortunately, these large models suffer from serious hallucination problems and tend to generate…

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…

A fundamental challenge in artificial intelligence involves understanding the cognitive mechanisms underlying visual reasoning in sophisticated models like Vision-Language Models (VLMs). How do these models integrate visual perception with…

Scaling LLM-based embodied agents from text-only environments to complex multimodal settings remains a major challenge. Recent work identifies a perception-reasoning-decision gap in standalone Vision-Language Models (VLMs), which often…

Large language models (LLMs) are increasingly trained to abstain on difficult questions by answering unknown. However, we observe that LLMs often misuse this option: they output unknown even when LLMs can actually solve the questions, or…

Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual claims. A good dense caption should be both faithful and…