3,690 items tracked: 31 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2610.14541v1 Announce Type: cross Abstract: Emerging strong Vision-Language Models (VLMs) have advanced navigation foundation models.
arXiv:2610.14701v1 Announce Type: cross Abstract: Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training.
arXiv:2610.14705v1 Announce Type: cross Abstract: Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging because prescription de…
arXiv:2610.14723v1 Announce Type: cross Abstract: A method integrating policy gradient with fuzzy inference has been proposed.
arXiv:2610.14730v1 Announce Type: cross Abstract: Adapting embedding models to new tasks requires training data that reflect task-specific information needs and relevance criteria.
arXiv:2610.14737v1 Announce Type: cross Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate actions.
arXiv:2610.14776v1 Announce Type: cross Abstract: Text-to-speech (TTS) systems are conventionally optimized for intelligibility and speaker similarity.
arXiv:2610.14812v1 Announce Type: cross Abstract: Three-dimensional (3D) velocity model building (VMB) remains computationally challenging with conventional approaches and native 3D neural networks, largely due to the pr…
arXiv:2610.14852v1 Announce Type: cross Abstract: Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accurate rewards and eff…
arXiv:2610.14960v1 Announce Type: cross Abstract: Can an autonomous AI agent reverse engineer a binary as well as a skilled human analyst?
arXiv:2610.14998v1 Announce Type: cross Abstract: Tabular foundation models adapt to new datasets through in-context learning (ICL), and, like most transformers, they tie computational depth to the number of independentl…
arXiv:2610.15029v1 Announce Type: cross Abstract: Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextual understanding and…
arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next.
arXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally recognized human righ…
arXiv:2610.15207v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass safety alignment and…
arXiv:2610.15244v1 Announce Type: cross Abstract: Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to emerge only after dep…
arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them.
arXiv:2610.15267v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) learn world models directly in latent space, but unconstrained autoregressive predictors may contract the latent distribu…
arXiv:2610.15297v1 Announce Type: cross Abstract: Recently, AutoRegressive Visual Generation (ARVG) models have emerged as a competitive paradigm for high-quality image synthesis.
arXiv:2610.15343v1 Announce Type: cross Abstract: World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threats remains largely…
arXiv:2610.15371v1 Announce Type: cross Abstract: Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in English and eight Indian…
arXiv:2610.15415v1 Announce Type: cross Abstract: Before an agent acts, it must decide whether action is warranted.
arXiv:2610.15429v1 Announce Type: cross Abstract: How do we tell a world model what information to preserve?
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks.
arXiv:2610.15509v1 Announce Type: cross Abstract: KV caches make long-context serving efficient by reusing past computation, but model switching breaks this reuse and forces the receiver to prefill the context again.
arXiv:2610.15518v1 Announce Type: cross Abstract: Probabilistic ocean modeling is essential for risk-aware marine operations, climate analysis, and scientific decision-making, where downstream decisions depend on the con…
arXiv:2610.15681v1 Announce Type: cross Abstract: Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design goals are expressed t…
arXiv:2610.15711v1 Announce Type: cross Abstract: Do genomic foundation models (FMs) provide predictive information beyond simple sequence composition?
arXiv:2610.15724v1 Announce Type: cross Abstract: Denoising Diffusion Probabilistic Models have emerged as powerful generative priors across domains ranging from molecular design to high-resolution image synthesis.
arXiv:2610.15725v1 Announce Type: cross Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to unauthorized copying and…
arXiv:2610.15766v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) and vision--language--action models have provided robots with new capabilities for long-horizon task understanding and pla…
arXiv:2610.15840v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assigning credit to individ…
arXiv:2610.15883v1 Announce Type: cross Abstract: Text wrapped in a trigger can be made behaviorally invisible to a language model: omitted from summaries and quotations, ignored in question answering, and left unflagged…
arXiv:2610.15897v1 Announce Type: cross Abstract: Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result.
arXiv:2610.15924v1 Announce Type: cross Abstract: Agent environments are essential for large language model (LLM) development.
arXiv:2610.15976v1 Announce Type: cross Abstract: This paper investigates a new role of randomness in stochastic policies--as a medium for embedding and communicating information.
arXiv:2610.16027v1 Announce Type: cross Abstract: Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback.
arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to one authorized agent…
arXiv:2610.16067v1 Announce Type: cross Abstract: Agent evaluation harnesses are software systems that run test suites, generate inputs, and decide outcomes with test oracles.
arXiv:2610.16071v1 Announce Type: cross Abstract: Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes.
arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challenging.
arXiv:2610.16232v1 Announce Type: cross Abstract: In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit mo…
arXiv:2610.16491v1 Announce Type: cross Abstract: Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget.
arXiv:2610.16567v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) have achieved high success rates on familiar manipulation tasks, yet it remains unclear whether such scores reflect genuine zero-shot…
arXiv:2610.16622v1 Announce Type: cross Abstract: With the advancement in language modeling, research on adversarial images has recently shifted from image classifiers to vision-language models (VLMs).
arXiv:2610.16630v1 Announce Type: cross Abstract: Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions underlying secondary p…
arXiv:2610.16713v1 Announce Type: cross Abstract: Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors.
arXiv:2610.16735v1 Announce Type: cross Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response.
arXiv:2610.16763v1 Announce Type: cross Abstract: Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action?
arXiv:2610.16778v1 Announce Type: cross Abstract: Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally identifiable information (PII).