Stay updated with the latest research and technology news
arXiv:2602.06843v1 Announce Type: new Abstract: A central question in cognitive science is whether conceptual representations converge onto a shared manifold to support generalization, or diverge...
arXiv:2602.06846v1 Announce Type: new Abstract: Spatial audio is crucial for creating compelling immersive 360-degree video experiences. However, generating realistic spatial audio, such as first-order ambisonics...
arXiv:2602.06849v1 Announce Type: new Abstract: Discrete diffusion models have emerged as a powerful paradigm for generative modeling on sequence data; however, the information-theoretic principles governing...
arXiv:2602.06850v1 Announce Type: new Abstract: While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like...
arXiv:2602.06854v1 Announce Type: new Abstract: Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing...
arXiv:2602.06858v1 Announce Type: new Abstract: The loss function is crucial to machine learning, especially in supervised learning frameworks. It is a fundamental component that controls...
arXiv:2602.06859v1 Announce Type: new Abstract: Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD...
arXiv:2602.06860v1 Announce Type: new Abstract: Range queries are simple and popular types of queries used in data retrieval. However, extracting exact and complete information using...
arXiv:2602.06862v1 Announce Type: new Abstract: Adapting pre-trained vision models using parameter-efficient fine-tuning (PEFT) remains challenging, as it aims to achieve performance comparable to full fine-tuning...
arXiv:2602.06864v1 Announce Type: new Abstract: Robotic tasks involving contact interactions pose significant challenges for trajectory optimization due to discontinuous dynamics. Conventional formulations typically assume deterministic...
arXiv:2602.06866v1 Announce Type: new Abstract: Reliable short-term demand forecasting is essential for managing shared micro-mobility services and ensuring responsive, user-centered operations. This study introduces T-STAR...
arXiv:2602.06868v1 Announce Type: new Abstract: Zero-order optimization has recently received significant attention for designing optimal trajectories and policies for robotic systems. However, most existing methods...
arXiv:2602.06869v1 Announce Type: new Abstract: We study a persistent failure mode in multi-objective alignment for large language models (LLMs): training improves performance on only a...
arXiv:2602.06871v1 Announce Type: new Abstract: Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress,...
arXiv:2602.06872v1 Announce Type: new Abstract: We derive a residual-based $hp$-a posteriori error estimator for hybrid high-order (HHO) methods on simplicial meshes applied to the biharmonic...
arXiv:2602.06873v1 Announce Type: new Abstract: This paper studies the integration problem in differential fields that may involve quantities reminiscent of the Weierstrass $\wp$ function, which...
arXiv:2602.06875v1 Announce Type: new Abstract: Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods...
arXiv:2602.06879v1 Announce Type: new Abstract: While large-scale text-to-image diffusion models continue to improve in visual quality, their increasing scale has widened the gap between state-of-the-art...
arXiv:2602.06880v1 Announce Type: new Abstract: Adaptive methods like Adam have become the $\textit{de facto}$ standard for large-scale vector and Euclidean optimization due to their coordinate-wise...
arXiv:2602.06883v1 Announce Type: new Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness....
arXiv:2602.06884v1 Announce Type: new Abstract: Image-based patient-specific simulation of left ventricular (LV) mechanics is valuable for understanding cardiac function and supporting clinical intervention planning, but...
arXiv:2602.06886v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information flow between text tokens...
arXiv:2602.06887v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However, existing backdoor defenses...
arXiv:2602.06899v1 Announce Type: new Abstract: Recovering a unique causal graph from observational data is an ill-posed problem because multiple generating mechanisms can lead to the...