Related papers: AStar: Boosting Multimodal Reasoning with Automate…

Current Multimodal Large Language Models (MLLMs) excel in general visual reasoning but remain underexplored in Abstract Visual Reasoning (AVR), which demands higher-order reasoning to identify abstract rules beyond simple perception.…

Large Language Models (LLMs) have achieved strong performance on static reasoning benchmarks, yet their effectiveness as interactive agents operating in adversarial, time-sensitive environments remains poorly understood. Existing…

Given the increasing scale of model sizes, novel training strategies like gradual stacking [Gong et al., 2019, Reddi et al., 2023] have garnered interest. Stacking enables efficient training by gradually growing the depth of a model in…

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…

Multimodal sarcasm detection requires resolving pragmatic incongruity across textual, acoustic, and visual cues through cross-modal reasoning. To enable robust sarcasm reasoning with foundation models, we propose SarcasmMiner, a…

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

Recent test-time reasoning methods improve performance by generating more candidate chains or searching over larger reasoning trees, but they typically lack explicit control over when to expand, what to prune, how to repair, and when to…

As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods…

Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this…

Chain of thought finetuning (cot-finetuning) aims to endow small language models (SLM) with reasoning ability to improve their performance towards specific tasks by allowing them to imitate the reasoning procedure of large language models…

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose…

Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimization treat sampled trajectories as independent chains,…

Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large language models show promise in artwork explanation, they rely on implicit reasoning and…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

Achieving robust spatial reasoning remains a fundamental challenge for current Multimodal Foundation Models (MFMs). Existing methods either overfit statistical shortcuts via 3D grounding data or remain confined to 2D visual perception,…

Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distillation, can be a cost-effective way to boost reasoning…

Recent advancements in large-scale models, such as GPT-4, have showcased remarkable capabilities in addressing standard queries. However, when facing complex problems that require multi-step logical reasoning, their accuracy dramatically…

Human reasoning relies on constructing and manipulating mental models -- simplified internal representations of situations used to understand and solve problems. Conceptual diagrams (e.g., a sketch drawn to aid reasoning) externalize these…