Stay updated with the latest research and technology news
arXiv:2602.12196v1 Announce Type: new Abstract: AI models have achieved state-of-the-art results in textual reasoning; however, their ability to reason over spatial and relational structures remains...
arXiv:2602.12194v1 Announce Type: new Abstract: In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user installs the...
arXiv:2602.12192v1 Announce Type: new Abstract: Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains...
arXiv:2602.12189v1 Announce Type: new Abstract: Biomedical signal classification presents unique challenges due to long sequences, complex temporal dynamics, and multi-scale frequency patterns that are poorly...
arXiv:2602.12187v1 Announce Type: new Abstract: Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to...
arXiv:2602.12183v1 Announce Type: new Abstract: The rapid evolution of cyberattacks continues to drive the emergence of unknown (zero-day) threats, posing significant challenges for network intrusion...
arXiv:2602.12182v1 Announce Type: new Abstract: We extend the recent analysis of the rate-reliability tradeoff in deterministic identification (DI) to general linear Gaussian channels, marking the...
arXiv:2602.12181v1 Announce Type: new Abstract: Convex Markov Games (cMGs) were recently introduced as a broad class of multi-agent learning problems that generalize Markov games to...
arXiv:2602.12180v1 Announce Type: new Abstract: Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize...
arXiv:2602.12178v1 Announce Type: new Abstract: Tomographic Volumetric Additive Manufacturing(TVAM) is a novel manufacturing method that allows for the fast creation of objects of complex geometry...
arXiv:2602.12177v1 Announce Type: new Abstract: State-of-the-art generative image and video models rely heavily on tokenizers that compress high-dimensional inputs into more efficient latent representations. While...
arXiv:2602.12175v1 Announce Type: new Abstract: The Joint Replenishment Problem (JRP) is a classical inventory management problem, that aims to model the trade-off between coordinating orders...
arXiv:2602.12173v1 Announce Type: new Abstract: Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for...
arXiv:2602.12172v1 Announce Type: new Abstract: Knowledge distillation from Large Language Models (LLMs) to smaller models has emerged as a critical technique for deploying efficient AI...
arXiv:2602.12170v1 Announce Type: new Abstract: In previous work (Coppola, 2024) we introduced the Quantified Boolean Bayesian Network (QBBN), a logical graphical model that implements the...
arXiv:2602.12164v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated exceptional reasoning capabilities, and co-evolving paradigms have shown promising results in domains such as...
arXiv:2602.12162v1 Announce Type: new Abstract: Molecular design encompasses tasks ranging from de-novo design to structural alteration of given molecules or fragments. For the latter, state-of-the-art...
arXiv:2602.12160v1 Announce Type: new Abstract: Recent advancements in foundation models have revolutionized joint audio-video generation. However, existing approaches typically treat human-centric tasks including reference-based audio-video...
arXiv:2602.12159v1 Announce Type: new Abstract: Object navigation is a core capability of embodied intelligence, enabling an agent to locate target objects in unknown environments. Recent...
arXiv:2602.12158v1 Announce Type: new Abstract: Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies...
arXiv:2602.12157v1 Announce Type: new Abstract: High-quality 3D texture generation remains a fundamental challenge due to the view-inconsistency inherent in current mainstream multi-view diffusion pipelines. Existing...
arXiv:2602.12155v1 Announce Type: new Abstract: Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning...
arXiv:2602.12153v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) represent a new paradigm beyond autoregressive modeling, offering competitive performance while naturally enabling a flexible...
arXiv:2602.12151v1 Announce Type: new Abstract: Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but...