Stay updated with the latest research and technology news
arXiv:2602.02192v3 Announce Type: replace Abstract: Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward...
arXiv:2602.02301v2 Announce Type: replace Abstract: Reinforcement learning (RL) has played a central role in recent advances in large reasoning models (LRMs), yielding strong gains in...
arXiv:2602.02306v2 Announce Type: replace Abstract: Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both...
arXiv:2602.02320v2 Announce Type: replace Abstract: Molecular function is largely determined by structure. Accurately aligning molecular structure with natural language is therefore essential for enabling large...
arXiv:2602.02335v2 Announce Type: replace Abstract: Lakehouses are the default cloud platform for analytics and AI, but they become unsafe when untrusted actors concurrently operate on...
arXiv:2602.02347v2 Announce Type: replace Abstract: Land management intensity shapes ecosystem service provision, socio-ecological resilience and is central to sustainable transformation. Yet most land use models...
arXiv:2602.02380v2 Announce Type: replace Abstract: Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style...
arXiv:2602.02495v2 Announce Type: replace Abstract: Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems...
arXiv:2602.02543v2 Announce Type: replace Abstract: Model editing has emerged as a practical approach for mitigating factual errors and outdated knowledge in large language models (LLMs)....
arXiv:2602.02599v3 Announce Type: replace Abstract: Long-context inference in large language models is increasingly bottlenecked by the memory and compute cost of the KV-Cache. Low-rank factorization...
arXiv:2602.02676v2 Announce Type: replace Abstract: Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual...
arXiv:2602.02948v2 Announce Type: replace Abstract: Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities...
arXiv:2602.03067v2 Announce Type: replace Abstract: Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at...
arXiv:2602.03201v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) achieves high sample efficiency by simulating future trajectories with learned dynamics and reward models. However, its...
arXiv:2602.03213v3 Announce Type: replace Abstract: Autonomous driving relies on robust models trained on large-scale, high-quality multi-view driving videos. Although world models provide a cost-effective solution...
arXiv:2602.03760v2 Announce Type: replace Abstract: Most vision models are trained on RGB images processed through ISP pipelines optimized for human perception, which can discard sensor-level...
arXiv:2602.03913v2 Announce Type: replace Abstract: Zero-shot Handwritten Chinese Character Recognition (HCCR) aims to recognize unseen characters by leveraging radical-based semantic compositions. However, existing approaches often...
arXiv:2602.04482v2 Announce Type: replace Abstract: Proactive agents that anticipate user intentions without explicit prompts represent a significant evolution in human-AI interaction, promising to reduce cognitive...
arXiv:2602.04567v2 Announce Type: replace Abstract: Short-video recommendation presents unique challenges, such as modeling rapid user interest shifts from implicit feedback, but progress is constrained by...
arXiv:2602.04909v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) and related methods align large language models from pairwise preferences by regularizing updates against a fixed...
arXiv:2602.04942v2 Announce Type: replace Abstract: Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful...
arXiv:2602.05195v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) promises grounded question answering, yet domain settings with multiple heterogeneous knowledge bases (KBs) remain challenging. In Chinese...
arXiv:2602.05474v2 Announce Type: replace Abstract: Motivation-based recommendation systems uncover user behavior drivers. Motivation modeling, crucial for decision-making and content preference, explains recommendation generation. Existing methods...
arXiv:2602.05589v2 Announce Type: replace Abstract: In this paper, a new class of \emph{Taylor-accelerated neural network interpolation operators} is introduced on quasi-uniform irregular grids. These operators...