Knowledge catalogue
arXiv:2510.01782v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal,
arXiv:2605.17528v1 Announce Type: cross Abstract: Large Language Models (LLMs) generate realistic synthetic data but offer no guarantee that their outputs respect the causal mechanisms governing the t
arXiv:2605.17458v1 Announce Type: new Abstract: Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise
arXiv:2605.16984v1 Announce Type: new Abstract: We present our submission to the LLM track of the 2026 Computational Models of Reference, Anaphora and Coreference (CRAC 2026) shared task. With an aver
arXiv:2605.17281v1 Announce Type: cross Abstract: Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation co
arXiv:2602.02979v2 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated strong potential in complex reasoning, yet their progress remains fundamentally constrained by reliance
arXiv:2605.18498v1 Announce Type: cross Abstract: Expert specialization in Mixture-of-Experts (MoE) models remains poorly understood, with traditional evaluations conflating architectural load-balanci
Disappointing pricing trend with Gemini 3.5 Flash. 22.5x pricier than 2.0 Flash which came out 15 months ago (9.00 vs 0.40). Are Flash models supposed to get this much more expensive, or is Pro just b
arXiv:2601.10705v3 Announce Type: replace Abstract: We study a semi-asynchronous client-server perceptron trained via iterative parameter mixing (IPM-style averaging): clients run local perceptron upd
arXiv:2605.16737v1 Announce Type: cross Abstract: End-to-End (E2E) autonomous driving models have shown growing capability in recent years, with performance improving on increasingly challenging bench
arXiv:2605.17109v1 Announce Type: cross Abstract: In recent years, Muon has emerged as the dominant method for training large language models, and transformers more broadly. The essential difference,
arXiv:2603.11689v2 Announce Type: replace Abstract: Frontier Multimodal Large Language Models (MLLMs) exhibit remarkable capabilities in Visual-Language Comprehension (VLC) tasks. However, they are of
arXiv:2605.18020v1 Announce Type: new Abstract: Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon se
arXiv:2605.18028v1 Announce Type: cross Abstract: Federated fine-tuning of Large Language Models faces severe statistical heterogeneity. However, existing model-level defenses often overlook the root
Cognition AI announced the availability of Gemini 3.5 Flash within Windsurf, their AI development environment. This integration brings Google's faster Gemini 3.5 Flash model to Windsurf users, likely
arXiv:2605.16389v1 Announce Type: cross Abstract: Haptic rendering of viscoelastic materials that exhibit creep and stress relaxation is crucial for many applications, such as medical training with re
arXiv:2504.03035v2 Announce Type: replace-cross Abstract: Random feature ridge regression is often analyzed in the high-dimensional regime under the homogeneous sampling model x_i=Sigma^{1/2}x_i', whe
arXiv:2605.16665v1 Announce Type: new Abstract: Continental-scale knowledge of subsurface temperature is limited by the cost and sparsity of borehole measurements, but such information is essential fo
arXiv:2602.17679v2 Announce Type: replace Abstract: Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing
arXiv:2605.17256v1 Announce Type: cross Abstract: This work introduces a latency-aware benchmarking framework for evaluating deep learning models in power system anomaly detection using high-fidelity,
arXiv:2605.16358v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, se
arXiv:2510.04006v2 Announce Type: replace Abstract: Data-driven machine learning (ML) models are reshaping weather forecasting and have shown the potential to accelerate and surpass traditional physic
arXiv:2605.18681v1 Announce Type: new Abstract: Explainable AI (XAI) techniques are increasingly important for the validation and responsible use of modern deep learning models, but are difficult to e
arXiv:2605.16343v1 Announce Type: cross Abstract: Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer blocks, enabling deeper computation under a fixed mod
arXiv:2605.17292v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks as
arXiv:2605.18549v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not alwa
Google's Gemini 3.5 Flash model costs approximately 3x more than Gemini 3 Flash, despite being a newer version. Google plans to integrate Gemini 3.5 Flash into many of their own products, suggesting t
arXiv:2605.17596v1 Announce Type: new Abstract: We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions
arXiv:2605.18583v1 Announce Type: cross Abstract: Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than a
arXiv:2605.16881v1 Announce Type: new Abstract: Digital humanities projects increasingly rely on machine translation and large language models to widen access to classical, religious, and otherwise un
arXiv:2603.23231v2 Announce Type: replace Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. Existing evaluations of t
arXiv:2605.17187v1 Announce Type: cross Abstract: Social media are shifting towards pluralism -- community-governed platforms where groups define their own norms. What violates rules in one community
arXiv:2605.18053v1 Announce Type: cross Abstract: We study KV cache eviction under a shared globally capped decode-time harness. Seven policies (LRU, H2O, SnapKV, StreamingLLM, Ada-KV, QUEST, Random)
arXiv:2510.12534v4 Announce Type: replace Abstract: The rapid growth of user-generated text across digital platforms has intensified the need for interpretable models capable of fine-grained text clas
Gemini Omni is an extension of Google's Gemini model that enhances its multimodal capabilities by enabling seamless integration of text, audio, image, and video inputs and outputs. This advancement al
arXiv:2510.18822v4 Announce Type: replace Abstract: Due to the varying granularity of target states across different tasks, most existing trackers are tailored to a single task, which specificity limi
arXiv:2605.17311v1 Announce Type: new Abstract: The remarkable visual fidelity of recent commercial video generative models, such as Sora and Veo, renders robust AI-generated video detection increasin
arXiv:2605.17991v1 Announce Type: cross Abstract: Stable Audio 3 is a family of fast latent diffusion models (small, medium, large) for variable-length audio generation and editing. Since our models c
arXiv:2605.16486v1 Announce Type: cross Abstract: Diffusion and flow-based models are ubiquitously used for generative modelling and density estimation. They admit a deterministic probability flow ord
arXiv:2605.17273v1 Announce Type: cross Abstract: State-of-the-Art (SOTA) claims pervade Artificial Intelligence (AI) and Machine Learning (ML) research. These claims rest on benchmark evaluations, wh
arXiv:2502.13957v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deplo
arXiv:2605.18109v1 Announce Type: new Abstract: In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean
arXiv:2602.21265v2 Announce Type: replace Abstract: We introduce ToolMATH, a math-grounded diagnostic benchmark for evaluating long-horizon tool use under controllable tool-catalog conditions. ToolMAT
arXiv:2409.10102v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although ex
arXiv:2509.23986v2 Announce Type: replace Abstract: Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such too
arXiv:2605.18740v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evide
arXiv:2605.18172v1 Announce Type: new Abstract: Leveraging the universal representations of pre-trained LLMs and MLLMs offers a promising path toward brain foundation models. However, visually-evoked
arXiv:2605.18313v1 Announce Type: cross Abstract: Small vision-language models (2-8B) are well-suited for clin- ical deployment due to privacy constraints, limited connectivity, and low-latency requir
arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag
arXiv:2605.17173v1 Announce Type: cross Abstract: Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds
arXiv:2605.15314v1 Announce Type: new Abstract: We study nonconvex stochastic optimization under the Blum-Gladyshev (mathsf{BG}-0) noise model, where the stochastic gradient variance grows quadratical
arXiv:2605.15736v1 Announce Type: cross Abstract: Biomedical Vision--Language Models (VLMs) have shown remarkable promise in few-shot medical diagnosis but face a critical bottleneck: extit{fragility
arXiv:2605.15734v1 Announce Type: new Abstract: The use of large language models to assess user states in conversational and adaptive systems is based on the assumption that the metrics used for such
arXiv:2605.15325v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong performance in video anomaly detection (VAD) while providing interpretable predictions. However, existin
arXiv:2605.15684v1 Announce Type: new Abstract: The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffus
arXiv:2605.16215v1 Announce Type: new Abstract: Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, reproducible validation. Yet current LLM-based CDS
arXiv:2605.15223v1 Announce Type: cross Abstract: This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-Language Models (VLMs) and Model-Driven Engineering
arXiv:2605.15411v1 Announce Type: cross Abstract: We study contextual dynamic pricing in a semiparametric scalar-index valuation model where the latent value is v_t=mu_ast(mathsf c_t)+xi_t, with an un
arXiv:2605.15338v1 Announce Type: cross Abstract: Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for pe
arXiv:2603.17915v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are deployed in multilingual settings, their safety behavior in culturally diverse, low-resource languages rem