95
归档文章
8
活跃日期
8
新闻源
arXiv cs.AI
47 articles
Latest: Jun 19, 2026
arXiv cs.LG
18 articles
Latest: Jun 19, 2026
arXiv cs.CL
15 articles
Latest: Jun 19, 2026
The Decoder
5 articles
Latest: Jun 19, 2026
Hugging Face
3 articles
Latest: Jun 17, 2026
MIT Tech Review AI
2 articles
Latest: Jun 19, 2026
OpenAI
2 articles
Latest: Jun 3, 2026
TechCrunch
1 article
Latest: Jun 19, 2026
For the last 30 years, stopping the flow of cybersecurity-related software has proven to be ineffective. It's unclear why it would work now with Anthropic’s cybersecurity model Mythos.
Amazon MGM Studios has dropped "Artificial," the nearly finished OpenAI film directed by Luca Guadagnino with Andrew Garfield as Sam Altman. Amazon struck a $50 billion partnership with OpenAI in February. According to…
Miami-based AI startup Subquadratic came out of stealth mode last month with a huge claim. It announced that it had solved a mathematical bottleneck that had been holding back large language models for almost a decade.…
OpenAI researchers show that reinforcement learning on desired behavioral traits like truthfulness and corrigibility works across domains. Training on health data also improved deception detection, and the model scored…
Two former OpenAI employees have built a website called "In the Weights" that reveals which people AI models can recall purely from their training data. A strength score of up to 996 shows how deeply a person is embedde…
arXiv:2606.19348v1 Announce Type: cross Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated)…
arXiv:2606.20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversa…
arXiv:2606.20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an…
arXiv:2606.19494v1 Announce Type: new Abstract: Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy, yet how and why it work…
arXiv:2606.19509v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to structured clinical data, yet whether they can recognize the limits of their own knowledge on such tasks remains u…
arXiv:2606.19559v1 Announce Type: new Abstract: Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insufficient for interactive large language model (LLM) agents and call for un…
arXiv:2606.19588v1 Announce Type: new Abstract: Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question can be formulated in l…
arXiv:2606.19607v1 Announce Type: new Abstract: Preference-based post-training has become a central paradigm for aligning language models. A common data-collection strategy is to generate a small set of completions for…
arXiv:2606.19704v1 Announce Type: new Abstract: Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coor…
arXiv:2606.19771v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instabi…
arXiv:2606.19787v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations res…
arXiv:2606.20138v1 Announce Type: new Abstract: LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subjec…
arXiv:2606.20245v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance across a wide range of language-based tasks by leveraging both extensive parametric knowledge and in-context…
arXiv:2606.20508v1 Announce Type: new Abstract: Prior work has shown that in-context demonstrations can jailbreak language models, but it remains unclear how models interpret different types of compliance demonstrations…
arXiv:2606.18716v1 Announce Type: cross Abstract: As AI agents are increasingly integrated into core business processes, understanding and designing effective interaction patterns between humans and AI agents becomes cr…
arXiv:2606.19344v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation. Standard audit…
arXiv:2606.19349v1 Announce Type: cross Abstract: While In-Context Learning (ICL) is extensively studied in Autoregressive (AR) LLMs, its mechanism within Diffusion Large Language Models (dLLMs) remains largely unexplor…
arXiv:2606.19366v1 Announce Type: cross Abstract: Information lattice learning (ILL) learns interpretable rules of a signal by alternately projecting the signal onto a partition lattice that encodes a hierarchy of abstr…
arXiv:2606.19376v1 Announce Type: cross Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality respo…
arXiv:2606.19387v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success in software development. However, they are susceptible to hallucinations, meaning that they can introduce s…
arXiv:2606.19474v1 Announce Type: cross Abstract: The transition to Post Quantum Cryptography (PQC) introduces considerable implementation complexity, requiring strict adherence to constant-time execution, side channel…
arXiv:2606.19528v1 Announce Type: cross Abstract: Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces…
arXiv:2606.19605v1 Announce Type: cross Abstract: Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain. We pr…
arXiv:2606.19727v1 Announce Type: cross Abstract: Language models have become essential tools in shaping modern workflows. However, their global effectiveness hinges on a nuanced understanding of local socio-cultural co…
arXiv:2606.19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with…
arXiv:2606.19899v1 Announce Type: cross Abstract: This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, o…
arXiv:2606.19950v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading t…
arXiv:2606.20014v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to spa…
arXiv:2606.20031v1 Announce Type: cross Abstract: Dynamic environmental changes, confined workspaces, and stringent real-time constraints make pathfinding in Robotic Mobile Fulfillment Systems (RMFS) a challenging probl…
arXiv:2606.20177v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to comprehend negation remains…
arXiv:2606.20258v1 Announce Type: cross Abstract: The emergence of LLM-driven information services is reshaping the conditions under which public knowledge institutions operate, threatening to absorb the editorial funct…
arXiv:2606.20373v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effe…
arXiv:2606.20436v1 Announce Type: cross Abstract: Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can…
arXiv:2606.20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Tra…
arXiv:2606.20510v1 Announce Type: cross Abstract: Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring approaches that formulate and enforce policies express…
arXiv:2606.20560v1 Announce Type: cross Abstract: LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. Howe…
arXiv:2602.00510v2 Announce Type: replace Abstract: Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraint…
arXiv:2606.15862v2 Announce Type: replace Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon…
arXiv:2606.19245v2 Announce Type: replace Abstract: Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires tru…
arXiv:2602.22495v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference…
arXiv:2603.19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-…
arXiv:2604.08552v2 Announce Type: replace-cross Abstract: Scientific metadata are often incomplete and noncompliant with community standards, limiting dataset findability, interoperability, and reuse. Even when standard…
arXiv:2604.11556v2 Announce Type: replace-cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to strengthen th…
arXiv:2606.03090v2 Announce Type: replace-cross Abstract: The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the stro…
arXiv:2606.16326v2 Announce Type: replace-cross Abstract: Paper A defines a time-consistent actuarial runtime that prices each side-effect-bearing action against a contractually fixed safe default and gates execution ag…
arXiv:2606.17165v2 Announce Type: replace-cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experime…
arXiv:2606.18272v2 Announce Type: replace-cross Abstract: This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language M…
arXiv:2606.19353v1 Announce Type: new Abstract: In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prom…
arXiv:2606.19468v1 Announce Type: new Abstract: The narrative composition of web-scale LLM pretraining corpora remains largely unexplored even though narrative is a fundamental mode of human communication. We present th…
arXiv:2606.19668v1 Announce Type: new Abstract: Multilingual Large Language Models (MLLMs) are increasingly expected to handle Code-Switched (CS) inputs, yet mixing languages frequently degrades performance relative to…
arXiv:2606.19847v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong reasoning and generation abilities, but their fixed context windows limit long-term information accumulation and reuse acro…
arXiv:2606.19852v1 Announce Type: new Abstract: Information extraction from pathology reports is essential for cancer staging, tumor registry population. Yet key data remains embedded in narrative reports, making manual…
arXiv:2606.19946v1 Announce Type: new Abstract: Activation steering controls model behavior by modifying intermediate hidden states at inference time without retraining. Existing methods handle only single-direction inj…
arXiv:2606.20482v1 Announce Type: new Abstract: To align a Large Language Model (LLM), most existing methods collect explicit human feedback and train a reward model to predict the human preference based on the response…
arXiv:2606.20527v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly deployed in personally and societally consequential settings, yet the visual cues that shape how these models jud…
arXiv:2606.19558v1 Announce Type: cross Abstract: Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality. We test…
arXiv:2603.25702v2 Announce Type: replace Abstract: Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block p…
arXiv:2605.17443v2 Announce Type: replace Abstract: We analyze how automatic speech recognition (ASR) errors propagate through ASR-LLM cascades in Korean spoken question answering (SQA), focusing on downstream semantic…
arXiv:2606.17041v3 Announce Type: replace Abstract: Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregation. Its structured,…
arXiv:2603.16941v2 Announce Type: replace-cross Abstract: Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in casca…
arXiv:2604.18105v2 Announce Type: replace-cross Abstract: Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a mainstream paradigm in recent years. Although existing LLM-based AS…
arXiv:2606.18941v2 Announce Type: replace-cross Abstract: PLCopen XML defines two encoding formats for IEC 61131-3 Ladder Diagram programs: a textual encoding using elements, and a graphical encoding that represents run…
arXiv:2606.19491v1 Announce Type: new Abstract: Pretrained transformers sit near singular minima of the loss, where the Fisher information metric degenerates along dead directions: directions in parameter space along wh…
arXiv:2606.19883v1 Announce Type: new Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model. To capture human pr…
arXiv:2606.19984v1 Announce Type: new Abstract: Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limited representational ca…
arXiv:2606.19993v1 Announce Type: new Abstract: We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that guides each weight matrix's low-rank approximation with a backward-sign…
arXiv:2606.20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off…
arXiv:2606.20107v1 Announce Type: new Abstract: Optimal Reinforcement Learning (RL) algorithms typically rely on carefully constructed count-based uncertainty estimates to drive exploration. Although theoretically sound…
arXiv:2606.20326v1 Announce Type: new Abstract: We develop QCPIKAN, the first quantum-classical physics-informed Kolmogorov-Arnold network designed to solve partial differential equations (PDEs). Built upon Chebyshev-po…
arXiv:2606.19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recen…
arXiv:2606.19989v1 Announce Type: cross Abstract: Modern LLM training breaks a core assumption behind offline batch samplers: the true training cost of a sample is only observable after preprocessing, augmentation, temp…
arXiv:2606.20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks. The number of inputs…
arXiv:2606.11171v2 Announce Type: replace Abstract: We develop indexed Bellman information complexity, a representation-level theory of interactive decision making centered on information indices and reference histories…
arXiv:2606.17832v2 Announce Type: replace Abstract: Large language models (LLMs) are often hypothesized to perform implicit Bayesian inference, yet a key coherence condition, the martingale property of predictive belief…
arXiv:2606.17886v2 Announce Type: replace Abstract: Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known…
arXiv:2606.18933v2 Announce Type: replace Abstract: Active feature acquisition (AFA) sequentially selects which features to observe to reach a classification or ranking decision. Its central limitation is reliance on la…
arXiv:2505.18726v3 Announce Type: replace-cross Abstract: Can we determine someone's geographic location solely from the sounds they hear? Are acoustic signals enough to localize within a country, state, or even city? I…
arXiv:2601.22300v3 Announce Type: replace-cross Abstract: We propose a deep photonic neuromorphic network (PNN) architecture based on phase-change material (PCM) synapses and local optical feedback for online, unsupervi…
arXiv:2606.14784v2 Announce Type: replace-cross Abstract: Understanding human states and interaction dynamics is a core goal of human-computer interaction (HCI). As interaction paradigms become more immersive, virtual r…
arXiv:2606.19149v2 Announce Type: replace-cross Abstract: Automated vulnerability discovery in large codebases remains challenging: traditional static analysis produces high false-positive rates, while dynamic approache…
OpenAI has upgraded ChatGPT's healthcare capabilities with GPT-5.5 Instant. In the company's own comparative tests, the model now outscores answers written by doctors in accuracy, clarity, and completeness. The error ra…
Claude Code can now turn work results into interactive web pages called "artifacts" and share them with your team. The pages pull from the full session context, update automatically when something changes, and keep a ve…
Chinese AI lab Z.ai released GLM-5.2 to their coding plan subscribers on June 13th, and then yesterday (June 16th) released the full open weights under an MIT license. Similar in size to their previous GLM-5 and GLM-5.1…