Related papers: A Logically Consistent Chain-of-Thought Approach f…
While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks. In this work, we study many-shot ICL on reasoning tasks, with a particular focus on many-shot…
Generating a Chain of Thought (CoT) has been shown to consistently improve large language model (LLM) performance on a wide range of NLP tasks. However, prior work has mainly focused on logical reasoning tasks (e.g. arithmetic, commonsense…
Deep learning has significantly improved the precision of instance segmentation with abundant labeled data. However, in many areas like medical and manufacturing, collecting sufficient data is extremely hard and labeling this data requires…
Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due to various practical concerns, e.g., data privacy or new surveillance deployments.…
Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…
Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…
Recent Vision-Language-Action (VLA) models for autonomous driving explore inference-time reasoning as a way to improve driving performance and safety in challenging scenarios. Most prior work uses natural language to express…
Stance detection on social media can help to identify and understand slanted news or commentary in everyday life. In this work, we propose a new model for zero-shot stance detection on Twitter that uses adversarial learning to generalize…
Zero-shot skeleton-based action recognition aims to recognize unseen actions by transferring knowledge from seen categories through semantic descriptions. Most existing methods typically align skeleton features with textual embeddings…
Current Large Language Model reasoning systems process queries independently, discarding valuable cross-instance signals such as shared reasoning patterns and consistency constraints. We introduce Batch-of-Thought (BoT), a training-free…
Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these step-by-step explanations reflect how the model actually reaches its answer, or merely…
Methods for object detection and segmentation often require abundant instance-level annotations for training, which are time-consuming and expensive to collect. To address this, the task of zero-shot object detection (or segmentation) aims…
In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. However, its performance on text-to-SQL parsing still has much room for improvement.…
In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…
The advancement of robotics and autonomous navigation systems hinges on the ability to accurately predict terrain traversability. Traditional methods for generating datasets to train these prediction models often involve putting robots into…
Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resulting in filled by redundant task-irrelevant shots. How to…
Large language models (LLMs) have demonstrated unprecedented capability in reasoning with natural language. Coupled with this development is the emergence of embodied AI in robotics. Despite showing promise for verbal and written reasoning…
Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the…
Many reasoning techniques for large multimodal models adapt language model approaches, such as Chain-of-Thought (CoT) prompting, which express reasoning as word sequences. While effective for text, these methods are suboptimal for…
Chain of Thought (CoT) of multi-step benefits from the logical structure of the reasoning steps and task-specific actions, significantly enhancing the mathematical reasoning capabilities of large language models. As the prevalence of long…