Stay updated with the latest research and technology news
arXiv:2602.14432v1 Announce Type: new Abstract: Activation outliers in large-scale transformer models pose a fundamental challenge to model quantization, creating excessively large ranges that cause severe...
arXiv:2602.14433v1 Announce Type: new Abstract: We present a system for autonomous book ideation that replaces human focus groups with synthetic reader panels -- diverse collections...
arXiv:2602.14434v1 Announce Type: new Abstract: Contact-rich manipulation tasks in unstructured environments pose significant robustness challenges for robot learning, where unexpected collisions can cause damage and...
arXiv:2602.14436v1 Announce Type: new Abstract: Collaborative virtual queueing has been proposed as a mechanism to mitigate airport surface congestion while preserving airline autonomy over aircraft-level...
arXiv:2602.14438v1 Announce Type: new Abstract: This study proposes an intelligent multi-agent framework built on LLMs and VLMs and specifically tailored to robotics. The goal is...
arXiv:2602.14441v1 Announce Type: new Abstract: Multimodal misinformation increasingly mixes realistic im-age edits with fluent but misleading text, producing persuasive posts that are difficult to verify....
arXiv:2602.14442v1 Announce Type: new Abstract: Visual impairments create barriers to learning physical activities, since conventional training methods rely on visual demonstrations or often inadequate verbal...
arXiv:2602.14443v1 Announce Type: new Abstract: Recent advances in image generation have achieved remarkable visual quality, while a fundamental challenge remains: Can image generation be controlled...
arXiv:2602.14444v1 Announce Type: new Abstract: Reasoning-specialized models like OpenAI's 5.1 and DeepSeek-V3.2 allocate substantial inference compute to extended chain-of-thought (CoT) traces, yet reasoning tokens incur...
arXiv:2602.14445v1 Announce Type: new Abstract: The Transformer architecture has become the foundation of modern deep learning, yet its core self-attention mechanism suffers from quadratic computational...
arXiv:2602.14449v1 Announce Type: new Abstract: Two-stage orthogonalization is essential in numerical algorithms such as Krylov subspace methods. For this task we need to orthogonalize a...
arXiv:2602.14451v1 Announce Type: new Abstract: Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate...
arXiv:2602.14452v1 Announce Type: new Abstract: Large Language Models (LLMs) offer strong capabilities but incur high inference costs due to dense computation and memory access. Training-free...
arXiv:2602.14456v1 Announce Type: new Abstract: Revealing the underlying causal mechanisms in the real world is crucial for scientific and technological progress. Despite notable advances in...
arXiv:2602.14457v1 Announce Type: new Abstract: To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework...
arXiv:2602.14462v1 Announce Type: new Abstract: Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter...
arXiv:2602.14464v1 Announce Type: new Abstract: Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While...
arXiv:2602.14466v1 Announce Type: new Abstract: With natural language generation becoming a popular use case for language models, the Bias Benchmark for Question-Answering (BBQ) has grown...
arXiv:2602.14467v1 Announce Type: new Abstract: Many real-world decisions rely on information search, where people sample evidence and decide when to stop under uncertainty. The uncertainty...
arXiv:2602.14468v1 Announce Type: new Abstract: Reinforcement learning (RL) has enhanced the capabilities of large language models (LLMs) through reward-driven training. Nevertheless, this process can introduce...
arXiv:2602.14469v1 Announce Type: new Abstract: Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but runs the risk of producing post-hoc rationalizations: when models...
arXiv:2602.14470v1 Announce Type: new Abstract: Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop...
arXiv:2602.14471v1 Announce Type: new Abstract: Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally...
arXiv:2602.14473v1 Announce Type: new Abstract: Quadruped robots are employed in various scenarios in building construction. However, autonomous stair climbing across different indoor staircases remains a...