Stay updated with the latest research and technology news
arXiv:2601.22984v1 Announce Type: new Abstract: Diagnosing the failure mechanisms of Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evaluation,...
arXiv:2601.22985v1 Announce Type: new Abstract: We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens...
arXiv:2601.22987v1 Announce Type: new Abstract: We present ArabicDialectHub, a cross-dialectal Arabic learning resource comprising 552 phrases across six varieties (Moroccan Darija, Lebanese, Syrian, Emirati, Saudi,...
arXiv:2601.22988v1 Announce Type: new Abstract: Real-world robotic manipulation demands visuomotor policies capable of robust spatial scene understanding and strong generalization across diverse camera viewpoints. While...
arXiv:2601.22990v1 Announce Type: new Abstract: Reconstructing 3D fetal MR volumes from motion-corrupted stacks of 2D slices is a crucial and challenging task. Conventional slice-to-volume reconstruction...
arXiv:2601.22993v1 Announce Type: new Abstract: We introduce the Value-at-Risk Constrained Policy Optimization algorithm (VaR-CPO), a sample efficient and conservative method designed to optimize Value-at-Risk (VaR)...
arXiv:2601.22996v1 Announce Type: new Abstract: Large Language Model (LLM) inference presents a unique scheduling challenge due to the Key-Value (KV) cache, where a job's memory...
arXiv:2601.22997v1 Announce Type: new Abstract: Agentic AI systems act through tools and evolve their behavior over long, stochastic interaction traces. This setting complicates assurance, because...
arXiv:2601.23000v1 Announce Type: new Abstract: While large language models (LLMs) have emerged as a significant advancement in artificial intelligence, the hardware and computational costs for...
arXiv:2601.23001v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing...
arXiv:2601.23006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing...
arXiv:2601.23007v1 Announce Type: new Abstract: Deep learning-based object detectors have achieved impressive performance in microscopy imaging, yet their confidence estimates often lack calibration, limiting their...
arXiv:2601.23009v1 Announce Type: new Abstract: Smart contracts are the backbone of the decentralized web, yet ensuring their functional correctness and security remains a critical challenge....
arXiv:2601.23010v1 Announce Type: new Abstract: Offline Reinforcement Learning (RL) relies on policy constraints to mitigate extrapolation error, where both the constraint form and constraint strength...
arXiv:2601.23011v1 Announce Type: new Abstract: Reliable control of myoelectric prostheses is often hindered by high inter-subject variability and the clinical impracticality of high-density sensor arrays....
arXiv:2601.23014v1 Announce Type: new Abstract: Memory agents, which depart from predefined memory-processing pipelines by endogenously managing the processing, storage, and retrieval of memories, have garnered...
arXiv:2601.23018v1 Announce Type: new Abstract: In highly competitive software markets, user experience (UX) evaluation is crucial for ensuring software quality and fostering long-term product success....
arXiv:2601.23020v1 Announce Type: new Abstract: Open-source software (OSS) dependencies are a dominant component of modern software code bases. Using proven and well-tested OSS components lets...
arXiv:2601.23026v1 Announce Type: new Abstract: Root cause analysis of anomalies aims to identify those features that cause the deviation from the normal process. Existing methods...
arXiv:2601.23027v1 Announce Type: new Abstract: Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly...
arXiv:2601.23032v1 Announce Type: new Abstract: Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to solve complex tasks by interacting with external tools, yet existing approaches...
arXiv:2601.23038v1 Announce Type: new Abstract: Mobile robots have become indispensable for exploring hostile environments, such as in space or disaster relief scenarios, but often remain...
arXiv:2601.23039v1 Announce Type: new Abstract: Differentiable matching layers, often implemented via entropy-regularized Optimal Transport, serve as a critical approximate inference mechanism in structural prediction. However,...
arXiv:2601.23041v1 Announce Type: new Abstract: Vision Language Models (VLMs) achieve strong performance on multimodal tasks but still suffer from hallucination and safety-related failures that persist...