Related papers: What's Holding Back Latent Visual Reasoning?

Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual reasoning, they remain fragile to viewpoint changes, as…

Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evidence from both modalities. A central limitation is that…

Detecting AI-generated images with multimodal large language models (MLLMs) has gained increasing attention, due to their rich world knowledge, common-sense reasoning, and potential for explainability. However, naively applying those MLLMs…

Chain-of-thought (CoT) reasoning has been highly successful in solving complex tasks in natural language processing, and recent multimodal large language models (MLLMs) have extended this paradigm to video reasoning. However, these models…

Large Vision-Language Models (LVLMs) usually generate texts which satisfy context coherence but don't match the visual input. Such a hallucination issue hinders LVLMs' applicability in the real world. The key to solving hallucination in…

Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing high-level reasoning. Classical methods address this by…

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

A chief goal of artificial intelligence is to build machines that think like people. Yet it has been argued that deep neural network architectures fail to accomplish this. Researchers have asserted these models' limitations in the domains…

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

The emergent few-shot reasoning capabilities of Large Language Models (LLMs) have excited the natural language and machine learning community over recent years. Despite of numerous successful applications, the underlying mechanism of such…

Reasoning is a hallmark of human intelligence, enabling adaptive decision-making in complex and unfamiliar scenarios. In contrast, machine intelligence remains bound to training data, lacking the ability to dynamically refine solutions at…

Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…

Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead.…

Reasoning with a chain-of-thought (CoT) enables Large Language Models (LLMs) to solve complex tasks but incurs significant inference costs due to the generation of long rationales. We propose Thinking States, a method that performs…

Most vision-language models (VLMs) apply a large language model (LLM) as the decoder, where the response tokens are generated sequentially through autoregression. Therefore, the number of output tokens can be the bottleneck of the…

Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies…

Why do Vision Language Models (VLMs), despite success on standard benchmarks, often fail to match human performance on surprisingly simple visual reasoning tasks? While the underlying computational principles are still debated, we…

The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior stems from a reporting bias in their training data. That is, how people communicate about…

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…

Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs…