Stay updated with the latest research and technology news
arXiv:2602.05735v3 Announce Type: replace Abstract: In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance...
arXiv:2602.05819v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as collaborative partners in writing. However, this raises a critical challenge of authorship,...
arXiv:2602.05838v2 Announce Type: replace Abstract: Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy...
arXiv:2602.05892v2 Announce Type: replace Abstract: LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task...
arXiv:2602.06037v2 Announce Type: replace Abstract: Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most...
arXiv:2602.06218v2 Announce Type: replace Abstract: Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly...
arXiv:2602.06317v2 Announce Type: replace Abstract: We present the Condensate Theorem: attention sparsity is a learned topological property, not an architectural constraint. Through empirical analysis of...
arXiv:2602.06563v2 Announce Type: replace Abstract: While scaling laws for recommendation models have gained significant traction, existing architectures such as Wukong, HiFormer and DHEN, often struggle...
arXiv:2602.06566v2 Announce Type: replace Abstract: Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for...
arXiv:2602.06603v2 Announce Type: replace Abstract: Offline reinforcement learning (ORL) has shown potential for improving decision-making in healthcare. However, contemporary research typically aggregates patient data into...
arXiv:2602.06927v2 Announce Type: replace Abstract: Lewis' account of common knowledge in Convention describes the generation of higher-order expectations between agents as hinging upon agents' inductive...
arXiv:2602.07193v2 Announce Type: replace Abstract: Millions of users form emotional attachments to AI companions like Character AI, Replika, and ChatGPT. When these relationships end through...
arXiv:2602.07358v2 Announce Type: replace Abstract: Unlearnable examples (UE) have emerged as a practical mechanism to prevent unauthorized model training on private vision data, while extending...
arXiv:2602.07413v2 Announce Type: replace Abstract: There has been rapid and dramatic progress in learning complex visuo-motor manipulation skills from demonstrations, thanks in part to expressive...
arXiv:2602.07449v2 Announce Type: replace Abstract: Achieving a balance between high-fidelity visual quality and low-latency streaming remains a formidable challenge in audio-driven portrait generation. Existing large-scale...
arXiv:2602.07451v2 Announce Type: replace Abstract: Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties,...
arXiv:2602.07513v2 Announce Type: replace Abstract: Multi-implementation systems are increasingly audited against natural-language specifications. Differential testing scales well when implementations disagree, but it provides little signal...
arXiv:2602.07519v2 Announce Type: replace Abstract: Simulations are an indispensable step in the cycle of theory development and refinement, helping researchers formulate precise definitions, generate models,...
arXiv:2602.07520v2 Announce Type: replace Abstract: Industrial recommender systems increasingly adopt multi-scenario learning (MSL) and multi-task learning (MTL) to handle diverse user interactions and contexts, but...
arXiv:2602.07529v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However,...
arXiv:2602.07543v2 Announce Type: replace Abstract: Material synthesis planning (MSP) remains a fundamental and underexplored bottleneck in AI-driven materials discovery, as it requires not only identifying...
arXiv:2602.07605v2 Announce Type: replace Abstract: Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While...
arXiv:2602.07629v2 Announce Type: replace Abstract: We propose LCLA (Language-Conditioned Latent Alignment), a framework for vision-language navigation that learns modular perception-action interfaces by aligning sensory observations...
arXiv:2602.07721v2 Announce Type: replace Abstract: KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale....