Stay updated with the latest research and technology news
arXiv:2602.06015v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being used in a zero-shot fashion to assess mental health conditions, yet we have...
arXiv:2602.06017v1 Announce Type: new Abstract: Video fusion is a fundamental technique in various video processing tasks. However, existing video fusion methods heavily rely on optical...
arXiv:2602.06018v1 Announce Type: new Abstract: This study is a first step towards using data-informed differential models to predict and control the dynamics of cancer-on-chip experiments....
arXiv:2602.06019v1 Announce Type: new Abstract: Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deploying...
arXiv:2602.06020v1 Announce Type: new Abstract: How do protein structure prediction models fold proteins? We investigate this question by tracing how ESMFold folds a beta hairpin,...
arXiv:2602.06022v1 Announce Type: new Abstract: Large language models (LLMs) exhibit persistent miscalibration, especially after instruction tuning and preference alignment. Modified training objectives can improve calibration,...
arXiv:2602.06023v1 Announce Type: new Abstract: Virtual reality (VR) has emerged as a powerful tool for evaluating school security measures in high-risk scenarios such as school...
arXiv:2602.06025v1 Announce Type: new Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems...
arXiv:2602.06026v1 Announce Type: new Abstract: Safety filtering is an effective method for enforcing constraints in safety-critical systems, but existing methods typically assume perfect state information....
arXiv:2602.06028v1 Announce Type: new Abstract: Recent approaches to real-time long video generation typically employ streaming tuning strategies, attempting to train a long-context student using a...
arXiv:2602.06029v1 Announce Type: new Abstract: Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and...
arXiv:2602.06030v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned...
arXiv:2602.06031v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine...
arXiv:2602.06032v1 Announce Type: new Abstract: Vision Foundation Models (VFMs) have achieved remarkable success when applied to various downstream 2D tasks. Despite their effectiveness, they often...
arXiv:2602.06033v1 Announce Type: new Abstract: Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning...
arXiv:2602.06034v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking....
arXiv:2602.06035v1 Announce Type: new Abstract: Humans rarely plan whole-body interactions with objects at the level of explicit whole-body movements. High-level intentions, such as affordance, define...
arXiv:2602.06036v1 Announce Type: new Abstract: Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor...
arXiv:2602.06037v1 Announce Type: new Abstract: Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most...
arXiv:2602.06038v1 Announce Type: new Abstract: To complete assignments provided by humans in natural language, robots must interpret commands, generate and answer relevant questions for scene...
arXiv:2602.06039v1 Announce Type: new Abstract: Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing pipelines rely on fixed, trajectory-wide...
arXiv:2602.06040v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However,...
arXiv:2602.06041v1 Announce Type: new Abstract: Multi-image spatial reasoning remains challenging for current multimodal large language models (MLLMs). While single-view perception is inherently 2D, reasoning over...
arXiv:2602.06042v1 Announce Type: new Abstract: The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization...