Knowledge catalogue
arXiv:2605.26657v1 Announce Type: new Abstract: Long-horizon decision problems with cumulative damage couple locally attractive actions to globally adverse outcomes. We identify two orthogonal failure
arXiv:2605.26990v1 Announce Type: cross Abstract: Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are un
arXiv:2601.21845v2 Announce Type: replace Abstract: Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling
arXiv:2605.26440v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has outpaced the scalability of traditional evaluation benchmarks, which remain heavily dependent
arXiv:2605.27076v1 Announce Type: cross Abstract: In many multi-agent applications, tasks yield rewards only when executed by a coalition meeting an unknown size threshold; otherwise, feedback is full
arXiv:2605.27115v1 Announce Type: new Abstract: Domain specialization can improve LLM behavior in vertical domains, but often weakens the general capabilities inherited from the original model. Recent
arXiv:2603.21563v2 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such s
arXiv:2605.26385v1 Announce Type: cross Abstract: Large-scale search, recommendation, and retrieval-augmented generation (RAG) systems typically employ a two-stage architecture: an early-stage ranker
arXiv:2605.26293v1 Announce Type: cross Abstract: Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves do
arXiv:2510.09405v2 Announce Type: replace Abstract: Radio frequency fingerprint identification (RFFI) is a key technique for wireless network security, leveraging intrinsic hardware imperfections to e
arXiv:2605.26365v1 Announce Type: new Abstract: Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping h
arXiv:2605.26315v1 Announce Type: cross Abstract: Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and exhibit
arXiv:2605.27157v1 Announce Type: new Abstract: Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robust
arXiv:2605.26262v1 Announce Type: new Abstract: Museums are important sites for the dissemination of culture and art. They are institutions rooted in history and tradition; their exhibitions are often
arXiv:2605.26236v1 Announce Type: new Abstract: Co-speech gesture generation requires both semantic expressivity and biomechanically plausible rhythmic motion. Existing holistic gesture models mix lex
arXiv:2605.26656v1 Announce Type: new Abstract: Multimodal large language models are typically trained end-to-end to predict ground-truth answers, yet supervision signals are applied exclusively to te
arXiv:2605.26952v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that ag
arXiv:2605.26478v1 Announce Type: cross Abstract: We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor con
arXiv:2605.26492v1 Announce Type: cross Abstract: LLM-generated stories are a popular use case, but they show very low variability. We sample 20,000 total stories from four current models using five p
Elon Musk on why humanity must become multiplanetary: “I think it's important for the long-term preservation and ultimately the expansion and extension of the scope and scale of consciousness... that
arXiv:2605.26785v1 Announce Type: cross Abstract: Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In advers
arXiv:2605.26637v1 Announce Type: new Abstract: Most existing embodied intelligence methods formulate perception, reasoning, planning, and control within a unified parameterized policy. Yet these capa
arXiv:2605.26332v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been
ESMFold2 represents an advancement in protein structure prediction leveraging scaling laws and transformer-based language models, building on principles that favor compute and data scale over hand-cra
arXiv:2603.13373v3 Announce Type: replace-cross Abstract: In ubiquitous and mobile health systems, computational models infer human states from wearable, behavioral, and physiological sensing data. In
arXiv:2501.06708v5 Announce Type: replace-cross Abstract: Large-scale web-crawled datasets contain noise, bias, and irrelevant information, necessitating data selection techniques. Existing methods de
arXiv:2605.27062v1 Announce Type: new Abstract: State-of-the-art performance for Automatic Speech Recognition (ASR) largely depends on the availability of large-scale labeled corpora. This creates a d
arXiv:2605.26589v1 Announce Type: cross Abstract: Childhood anemia affects around 40% of children aged 6-59 months globally and arises from heterogeneous factors, limiting model generalizability. We e
arXiv:2605.27333v1 Announce Type: new Abstract: Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary
arXiv:2603.17685v3 Announce Type: replace Abstract: Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochas
arXiv:2605.26423v1 Announce Type: new Abstract: Task-based fMRI provides a direct readout of task-evoked neural dynamics, but it is expensive and difficult to acquire at scale, motivating rest-to-task
arXiv:2605.26508v1 Announce Type: cross Abstract: We propose a foundational runtime actuarial layer for autonomous AI agents in which every side-effect-bearing action carries a time-consistent, counte
arXiv:2605.26926v1 Announce Type: new Abstract: Computing legal indicators from normative texts is a key task in legal monitoring and policy evaluation, but presents significant challenges due to the
arXiv:2605.26403v1 Announce Type: new Abstract: A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policie
arXiv:2605.26601v1 Announce Type: new Abstract: Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible trainin
arXiv:2605.26158v1 Announce Type: cross Abstract: Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshol
Gary's no way as bad as some people make him out to be. some data i shared yesterday on anthropic revenue possibly slowing down aren’t as a compelling as i thought; i have deleted my posts and await b
arXiv:2605.26857v1 Announce Type: new Abstract: Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector tran
arXiv:2602.16449v2 Announce Type: replace-cross Abstract: Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset re
arXiv:2605.27168v1 Announce Type: cross Abstract: Text embeddings are widely used to analyse large corpora of complex texts. However, it is unclear whether the embeddings capture the same semantic dis
arXiv:2605.26471v1 Announce Type: new Abstract: In dynamic urban logistics, the stochastic emergence of time-sensitive tasks poses a significant optimality challenge for heterogeneous AAVs logistics t
arXiv:2602.11799v2 Announce Type: replace Abstract: Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discr
arXiv:2508.18444v2 Announce Type: replace-cross Abstract: With the improving semantic understanding capability of Large Language Models (LLMs), they exhibit a greater awareness and alignment with huma
arXiv:2605.26638v1 Announce Type: new Abstract: Scaling data volume and diversity is critical for generalizing embodied intelligence. While synthetic data generation offers a scalable alternative to e
Gary Marcus expresses curiosity about the long-term outcomes of current developments, likely related to artificial intelligence or technology trends given his expertise in AI and cognitive science. Th
Jared Perlo / NBC News: Illinois Legislature passes SB 315, a bill requiring annual independent third-party safety audits of leading AI companies; the bill heads to the governor's desk — The measure,
arXiv:2605.27132v1 Announce Type: new Abstract: Multilevel image thresholding is widely used for segmentation in applications ranging from medical imaging to remote sensing. Classical objective functi
arXiv:2502.06963v3 Announce Type: replace-cross Abstract: The increasing complexity of Intelligent Transportation Systems (ITS) has led to significant interest in computational offloading to external
arXiv:2510.00902v2 Announce Type: replace Abstract: Transfer learning is crucial for medical imaging, yet the selection of source datasets often relies on researchers' intuition rather than systematic
arXiv:2605.27288v1 Announce Type: cross Abstract: Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behav
arXiv:2605.26409v1 Announce Type: cross Abstract: Evaluating and mitigating a generative system's susceptibility to jailbreak attacks is critical to its safe deployment. Given the number of deployable
arXiv:2605.26738v1 Announce Type: new Abstract: Human communication depends on implicit social signals where effectiveness is shaped by tone, context, and conversational norms rather than semantic con
arXiv:2605.26947v1 Announce Type: new Abstract: Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt datase
arXiv:2509.18384v2 Announce Type: replace Abstract: Large language models (LLMs) can translate natural language instructions into executable action plans for robotics, autonomous driving, and other do
arXiv:2605.26168v1 Announce Type: cross Abstract: Linux is the foundation of the digital age, accounting for the majority of the cloud and mobile OS markets. Any device that runs Linux uses the Linux
arXiv:2605.27063v1 Announce Type: new Abstract: The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node f
arXiv:2605.27046v1 Announce Type: new Abstract: Motor thermal management is often overlooked in the context of electrically-actuated robots, particularly legged robots, but motor overheating is a key
arXiv:2605.27073v1 Announce Type: new Abstract: Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coord
arXiv:2510.23486v2 Announce Type: replace Abstract: Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential de
arXiv:2605.27028v1 Announce Type: cross Abstract: On-policy distillation has recently emerged as a promising alternative to standard sequence-level imitation, training a student by scoring its own rol