Stay updated with the latest research and technology news
arXiv:2601.20326v1 Announce Type: new Abstract: KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks...
arXiv:2601.20327v1 Announce Type: new Abstract: Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional...
arXiv:2601.20330v1 Announce Type: new Abstract: While large language models show promise in mental healthcare, evaluating their therapeutic competence remains challenging due to the unstructured and...
arXiv:2601.20331v1 Announce Type: new Abstract: 3D Gaussian Splatting enables efficient optimization and high-quality rendering, yet accurate surface reconstruction remains challenging. Prior methods improve surface reconstruction...
arXiv:2601.20332v1 Announce Type: new Abstract: Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial...
arXiv:2601.20333v1 Announce Type: new Abstract: Deep topological data analysis (TDA) offers a principled framework for capturing structural invariants such as connectivity and cycles that persist...
arXiv:2601.20334v1 Announce Type: new Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and...
arXiv:2601.20335v1 Announce Type: new Abstract: Recent advances in mobile Graphical User Interface (GUI) agents highlight the growing need for comprehensive evaluation benchmarks. While new online...
arXiv:2601.20339v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) offer order-agnostic generation that can explore many possible decoding trajectories. However, current decoding methods commit to...
arXiv:2601.20346v1 Announce Type: new Abstract: Ransomware has become one of the most serious cybersecurity threats causing major financial losses and operational disruptions worldwide.Traditional detection methods...
arXiv:2601.20347v1 Announce Type: new Abstract: Multimodal evidence is critical in computational pathology: gigapixel whole slide images capture tumor morphology, while patient-level clinical descriptors preserve complementary...
arXiv:2601.20351v1 Announce Type: new Abstract: Palmprint recognition is widely used in biometric systems, yet real-world performance often degrades due to feature distribution shifts caused by...
arXiv:2601.20352v1 Announce Type: new Abstract: The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and...
arXiv:2601.20354v1 Announce Type: new Abstract: Text-to-image (T2I) models have achieved remarkable success in generating high-fidelity images, but they often fail in handling complex spatial relationships,...
arXiv:2601.20355v1 Announce Type: new Abstract: Scene graphs provide structured abstractions for scene understanding, yet they often overfit to spurious correlations, severely hindering out-of-distribution generalization. To...
arXiv:2601.20357v1 Announce Type: new Abstract: Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel....
arXiv:2601.20361v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) solve time-dependent partial differential equations (PDEs) by learning a mesh-free, differentiable solution that can be evaluated...
arXiv:2601.20362v1 Announce Type: new Abstract: Recent neural audio compression models often rely on residual vector quantization for high-fidelity coding, but using a fixed number of...
arXiv:2601.20363v1 Announce Type: new Abstract: Can standard continuous-time generative models represent distributions whose support is an extremely sparse, globally constrained discrete set? We study this...
arXiv:2601.20364v1 Announce Type: new Abstract: RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data...
arXiv:2601.20366v1 Announce Type: new Abstract: The integration of physical security systems with environmental safety monitoring represents a critical advancement in smart infrastructure management. Traditional approaches...
arXiv:2601.20367v1 Announce Type: new Abstract: Identifying safety-critical scenarios is essential for autonomous driving, but the rarity of such events makes supervised labeling impractical. Traditional rule-based...
arXiv:2601.20368v1 Announce Type: new Abstract: Recently, a novel peer sampling protocol, Elevator, was introduced to construct network topologies tailored for emerging decentralized applications such as...
arXiv:2601.20369v1 Announce Type: new Abstract: Crowd counting remains challenging in variable-density scenes due to scale variations, occlusions, and the high computational cost of existing models....