Related papers: From Heads to Neurons: Causal Attribution and Stee…

Reward models (RMs) play a crucial role in aligning large language models (LLMs) with human preferences and enhancing reasoning quality. Traditionally, RMs are trained to rank candidate outputs based on their correctness and coherence.…

Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work. With the belief that…

Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `non-human' agents, such as the ones backed by large…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low sampling success and unstable training in complex tasks. We…

Large Reasoning Models (LRMs) generate explicit reasoning traces alongside final answers, yet the extent to which these traces influence answer generation remains unclear. In this work, we conduct a three-stage investigation into the…

Vision-language models (VLMs) are increasingly used as automated judges for multimodal systems, yet their scores provide no indication of reliability. We study this problem through conformal prediction, a distribution-free framework that…

Code-trained language models have proven to be highly effective for various code intelligence tasks. However, they can be challenging to train and deploy for many software engineering applications due to computational bottlenecks and memory…

Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel…

We introduce the Rule Network with Selective Logical Operators (RNS), a novel neural architecture that employs \textbf{selective logical operators} to adaptively choose between AND and OR operations at each neuron during training. Unlike…

Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate…

Vision-Language Navigation (VLN) is a task where agents learn to navigate following natural language instructions. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches exploit…

Representation learning on networks offers a powerful alternative to the oft painstaking process of manual feature engineering, and as a result, has enjoyed considerable success in recent years. However, all the existing representation…

Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic…

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

This paper investigates how LLMs encode inputs with typos. We hypothesize that specific neurons and attention heads recognize typos and fix them internally using local and global contexts. We introduce a method to identify typo neurons and…

Recent works have shown that Large Language Models (LLMs) could empower traditional neuro-symbolic models via programming capabilities to translate language into module descriptions, thus achieving strong visual reasoning results while…

Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resources. However, what pieces of information are understood in…

Recent advancements for large-scale pre-training with neural signals such as electroencephalogram (EEG) have shown promising results, significantly boosting the development of brain-computer interfaces (BCIs) and healthcare. However, these…

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations…

Large language models (LLMs) are still struggling in aligning with human preference in complex tasks and scenarios. They are prone to overfit into the unexpected patterns or superficial styles in the training data. We conduct an empirical…