Knowledge catalogue
arXiv:2601.21094v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safe
arXiv:2605.24270v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of mode
arXiv:2605.25492v1 Announce Type: new Abstract: Pairwise model comparisons drawn from foundation-model benchmarks ('A is safer than B') are read as quantitative verdicts but hinge on harness choices b
arXiv:2605.24468v1 Announce Type: new Abstract: Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and
arXiv:2605.25796v1 Announce Type: cross Abstract: Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to parag
arXiv:2605.23983v1 Announce Type: new Abstract: We investigate growth dynamics in deterministic equational discovery substrates. Across three toy domains (arithmetic, boolean, higher-order list; n=592
arXiv:2605.25054v1 Announce Type: cross Abstract: Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware T
arXiv:2605.24326v1 Announce Type: cross Abstract: The rapid scaling of large language model training requires distributing GPU resources across multiple data center buildings and regions. We refer to
arXiv:2503.11657v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities in natural language processing tasks requiring multi-step logical reasoning capabili
arXiv:2605.24992v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) has shown wide applicability in collaborative systems such as autonomous driving and smart cities for its ab
arXiv:2604.00499v2 Announce Type: replace Abstract: To schedule LLM inference, the extit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid he
arXiv:2601.05847v2 Announce Type: replace Abstract: We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the tas
arXiv:2605.24426v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning
arXiv:2605.25394v1 Announce Type: new Abstract: Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small
arXiv:2605.25073v1 Announce Type: cross Abstract: Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parame
arXiv:2605.25435v1 Announce Type: new Abstract: The rapid evolution of large language model (LLM)-driven autonomous agents has given rise to OpenClaw, a new class of open-source agent frameworks that
arXiv:2605.24903v1 Announce Type: cross Abstract: Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on ful
arXiv:2605.24067v1 Announce Type: cross Abstract: Most nowcasting systems, built on radar reflectivity, focus on current precipitation, ignoring the atmospheric precursors -- such as low-level converg
arXiv:2605.23915v1 Announce Type: cross Abstract: The Intelligent Driver Model (IDM) is a cornerstone of Adaptive Cruise Control (ACC), valued for its interpretable parameters and effectiveness in car
arXiv:2512.18508v3 Announce Type: replace-cross Abstract: Validation gating is a fundamental component of classical Kalman-based tracking systems. Only measurements whose normalized innovation squared
arXiv:2605.25745v1 Announce Type: new Abstract: Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost d
arXiv:2605.24989v1 Announce Type: cross Abstract: Scaling test-time compute has proven highly effective for language models, yet this opportunity remains largely unexplored for industrial Click-Throug
arXiv:2605.24986v1 Announce Type: cross Abstract: Generative pre-training via discrete diffusion provides dense reconstruction supervision across all feature fields simultaneously, mitigating represen
arXiv:2605.24541v1 Announce Type: cross Abstract: Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We stu
arXiv:2605.23967v1 Announce Type: cross Abstract: In biological systems, sensing is not performed by the brain alone: the body deforms, vibrates, and filters external stimuli before they are transduce
arXiv:2601.03014v3 Announce Type: replace-cross Abstract: Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces signi
arXiv:2605.24958v1 Announce Type: cross Abstract: Despite the strong performance of deep neural networks in modern Web and language applications, they remain vulnerable to adversarial attacks, especia
arXiv:2605.25424v1 Announce Type: cross Abstract: Existing LLM routing frameworks treat queries as independent events, neglecting the sequential nature of real-world user sessions constrained by globa
arXiv:2605.24384v1 Announce Type: cross Abstract: Language models (LMs) can exhibit systematic biases against speakers based on variations in their dialects, even in the absence of a dialect label, a
arXiv:2605.24058v1 Announce Type: cross Abstract: On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA ad
arXiv:2605.25680v1 Announce Type: cross Abstract: Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap
arXiv:2605.25548v1 Announce Type: cross Abstract: Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. Temporal-first approaches build pe
arXiv:2605.25160v1 Announce Type: new Abstract: Mobile GUI agents powered by large language models have progressed rapidly, creating urgent needs for realistic and comprehensive evaluation. Existing b
arXiv:2605.24195v1 Announce Type: cross Abstract: Sonar is often the only modality suitable for high-resolution imaging underwater due to light attenuation and turbidity. Forward-looking imaging sonar
arXiv:2605.24117v1 Announce Type: new Abstract: Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience c
arXiv:2605.23969v1 Announce Type: new Abstract: Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged tr
arXiv:2605.24371v1 Announce Type: cross Abstract: CT report generation (CTRG) requires models to summarize three-dimensional anatomical context and pathological findings from hundreds of axial slices.
arXiv:2510.15284v2 Announce Type: replace Abstract: Ensemble-based data assimilation (DA) methods have become increasingly popular due to their inherent ability to address nonlinear dynamic problems.
arXiv:2605.25949v1 Announce Type: cross Abstract: Neural PDE solvers have followed the scaling trajectory of vision and language, with recent foundation models reaching billions of parameters. We argu
arXiv:2512.05402v2 Announce Type: replace-cross Abstract: Bitcoin mining hardware acquisition requires strategic timing due to volatile markets, rapid technological obsolescence, and protocol-driven r
arXiv:2605.21740v2 Announce Type: replace Abstract: LLM agents have incredible potential for scientific discovery applications. However, the performance of LLM agents on real-world, small molecule dru
arXiv:2605.24433v1 Announce Type: cross Abstract: Flow-matching robot policies commonly use action-chunking inference for efficient closed-loop control, but chunk boundaries can introduce discontinuou
arXiv:2605.23949v1 Announce Type: cross Abstract: As Large Language Models (LLMs) evolve into interactive agents, understanding their behavioral alignment within human social dynamics becomes essentia
arXiv:2605.25109v1 Announce Type: new Abstract: Soft pneumatic actuators are widely used in soft robotics because they can produce large motions while remaining compliant enough to interact safely wit
arXiv:2511.19211v3 Announce Type: replace Abstract: This paper presents a systematic topology optimization framework for designing a soft pneumatic gripper (SPG), explicitly considering the design-dep
arXiv:2506.18543v2 Announce Type: replace-cross Abstract: The rapid proliferation of Large Language Models (LLMs) has heightened concerns regarding their exposure to jailbreak attacks, which craft adv
arXiv:2602.07666v3 Announce Type: replace-cross Abstract: DARPA's AI Cyber Challenge (AIxCC, 2023--2025) is the largest competition to date for building fully autonomous cyber reasoning systems (CRSs)
arXiv:2605.24845v1 Announce Type: new Abstract: Combinatorial counting problems pervade artificial intelligence, statistics, and discrete mathematics. Whether the task is enumerating subsets, multiset
arXiv:2605.25420v1 Announce Type: cross Abstract: Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed g
arXiv:2509.11379v3 Announce Type: replace-cross Abstract: We demonstrate that learning procedures that rely on aggregated labels, e.g., label information distilled from noisy responses, enjoy robustne
arXiv:2602.02544v2 Announce Type: replace-cross Abstract: While Diffusion Language Models (DLMs) offer a flexible, arbitrary-order alternative to the autoregressive paradigm, their non-causal nature p
arXiv:2605.24484v1 Announce Type: new Abstract: Generalist neural routing solvers have shown great potential in solving diverse vehicle routing problems (VRPs) with a unified model. However, existing
arXiv:2605.23943v1 Announce Type: new Abstract: Quantum cognition often explains order effects, contextuality, and violations of the law of total probability by replacing classical probability with qu
arXiv:2512.24008v3 Announce Type: replace Abstract: Personalized search demands the ability to model users' evolving, multi-dimensional information needs; a challenge for systems constrained by static
arXiv:2509.16139v5 Announce Type: replace Abstract: Predicting the extreme hydrodynamic response of porous and architected lattice materials is a fundamental challenge in high energy density physics,
arXiv:2605.25181v1 Announce Type: new Abstract: Existing Large Language Model (LLM) approaches to SystemVerilog Assertion (SVA) generation primarily focus on syntactic validity and formal verification
arXiv:2605.25232v1 Announce Type: cross Abstract: Direct Code2Code transformation remains challenging to control because it can preserve surface-level syntax while introducing semantic drift, hidden b
arXiv:2509.05614v3 Announce Type: replace-cross Abstract: Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been appl
arXiv:2605.24059v1 Announce Type: cross Abstract: We present a three-step recipe for identifying attention-head circuits in pretrained transformers. A per-head spectral signal -- the time-integrated p
arXiv:2605.24764v1 Announce Type: cross Abstract: [Abridged] - Spectral Retrieval is a plug-in re-ranking stage that interpolates between per-token MaxSim and mean-pool retrieval through a multi-scale