Knowledge catalogue
arXiv:2605.27378v1 Announce Type: new Abstract: Dental image analysis plays a pivotal role in supporting accurate diagnosis and treatment planning in oral healthcare. Although recent advances have pro
Orchid Security Inc. today extended its Identity Control Plane with a set of capabilities aimed at governing artificial intelligence agents, saying existing identity and access management models canno
arXiv:2605.28691v1 Announce Type: new Abstract: Diffusion Transformers achieve strong video generation quality, but the quadratic cost of full attention limits efficiency. We introduce OSP-Next, an ef
This post discusses various software architecture and distributed systems concepts including the Blackboard pattern, Domain-Driven Design (DDD), Command Query Responsibility Segregation (CQRS), and me
Our team at @AIatMeta is excited to announce ATLAS: one of the largest automated formalization efforts to date. ATLAS contains Lean 4 formalizations of both statements and proofs from 25+ mathematics
arXiv:2605.28214v1 Announce Type: cross Abstract: Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficie
arXiv:2605.28585v1 Announce Type: new Abstract: Communication-efficient distributed optimizers such as DiLoCo reduce synchronization costs by letting workers perform many local updates before aggregat
arXiv:2605.28267v1 Announce Type: new Abstract: We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of
arXiv:2605.27440v1 Announce Type: cross Abstract: Small changes to how a buyer phrases a question -- 'best CRM' vs 'top CRM' vs 'best CRM for a SaaS startup' -- produce substantially different brand r
arXiv:2601.23262v2 Announce Type: replace Abstract: We introduce a guided stochastic sampling method that augments sampling from diffusion models with physics-based guidance derived from partial diffe
arXiv:2605.27545v1 Announce Type: new Abstract: Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text
arXiv:2605.27992v1 Announce Type: new Abstract: Time series anomaly detection is critical for maintaining the reliability of mission-critical systems. While Transformer-based models like PatchTST have
arXiv:2506.10138v3 Announce Type: replace-cross Abstract: We partially reverse-engineer a convolutional recurrent neural network (RNN) trained with model-free reinforcement learning to play the box-pu
arXiv:2605.27816v1 Announce Type: new Abstract: Personalized Federated Learning (PFL) constitutes a novel paradigm that tailors Machine Learning (ML) models to individual clients, thereby furnishing p
arXiv:2605.27762v1 Announce Type: new Abstract: We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-res
arXiv:2505.17720v3 Announce Type: replace Abstract: Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where mach
arXiv:2601.18006v2 Announce Type: replace Abstract: We present PEAR (Pairwise Evaluation for Automatic Relative Scoring), a supervised quality estimation (QE) metric family that reframes reference-fre
arXiv:2605.28819v1 Announce Type: cross Abstract: Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstrea
arXiv:2605.28164v1 Announce Type: cross Abstract: Evolutionary computation offers a variety of tools to solve complex real-world optimization problems. However, research often focuses on smaller, simp
arXiv:2605.27980v1 Announce Type: cross Abstract: The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. While recent efforts have extend
Perplexity Computer is now available inside Microsoft Excel, Word, PowerPoint, and Outlook. Orchestrate across work with Computer directly in the side panel of your app to draft documents, model, buil
arXiv:2605.28806v1 Announce Type: cross Abstract: Long-term memory is increasingly important for personalized AI agents, yet existing benchmarks and methods remain largely text-centric. Even when imag
arXiv:2605.28037v1 Announce Type: new Abstract: Prompt-based personality control is a key technique for designing large language model (LLM) dialogue agents that behave consistently across social cont
arXiv:2605.27385v1 Announce Type: cross Abstract: Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal fo
arXiv:2503.01829v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion. While these capabilities can be used for s
arXiv:2605.28032v1 Announce Type: new Abstract: Large Language Models are increasingly applied in the petroleum industry, highlighting the need for a domain-specific evaluation framework. This study d
arXiv:2605.28226v1 Announce Type: new Abstract: Small-molecule drug discovery requires simultaneous optimization of numerous properties of candidate molecules. These properties can be investigated thr
arXiv:2605.28345v1 Announce Type: new Abstract: Progress in Prognostics and Health Management (PHM) is hindered by the lack of standardized and reusable evaluation practices across tasks, datasets, an
arXiv:2605.28068v1 Announce Type: new Abstract: Tree ensembles are machine learning models with strong predictive performance and interpretability, and remain widely used for tabular data. Standard pr
arXiv:2605.28232v1 Announce Type: new Abstract: Occupant comfort and grid-aware energy efficiency are competing objectives whose joint optimization depends critically on how reward functions are speci
Rashi Shrivastava / Forbes: Pittsburgh-based Gray Swan, which stress-tests AI models for top frontier AI labs, raised a 40M Series A at a 200M valuation co-led by Wing VC and Madrona — Gray Swan works
arXiv:2605.28354v1 Announce Type: new Abstract: Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a
arXiv:2305.06426v2 Announce Type: replace Abstract: Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high bloo
arXiv:2605.28201v1 Announce Type: new Abstract: Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into ext
arXiv:2605.27832v1 Announce Type: new Abstract: Large Language Models (LLMs) are being applied to increasingly difficult problems and use cases. To navigate their vast solution spaces effectively, LLM
arXiv:2605.28592v1 Announce Type: new Abstract: This note provides an interesting observation on casting partial least square (PLS) as a linearized self-attention so that PLS may be studied within the
arXiv:2601.15015v2 Announce Type: replace Abstract: Reinforcement learning (RL) has shown promising results in active flow control (AFC), yet progress in the field remains difficult to assess as exist
arXiv:2601.17354v5 Announce Type: replace Abstract: While 3D Gaussian Splatting (3DGS) enables real-time rendering, its training demands workstation-level compute and memory, making mobile deployment
arXiv:2605.28237v1 Announce Type: cross Abstract: Real-world navigation is fundamentally driven by Points of Interest (POIs), yet reaching a precise POI remains a critical 'final-meters' challenge. Ex
arXiv:2605.28241v1 Announce Type: new Abstract: Point cloud quality plays a critical role in 3D acquisition, reconstruction, rendering, and perception, yet existing point cloud quality assessment (PCQ
arXiv:2605.27631v1 Announce Type: cross Abstract: Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In thi
arXiv:2605.27887v1 Announce Type: new Abstract: LLMs have shown strong performance across diverse financial tasks, yet portfolio management (PM), a critical financial decision-making task, remains poo
arXiv:2605.28597v1 Announce Type: cross Abstract: This position paper argues that the AI/ML community should stop overclaiming and retire the label 'positive backdoor,' and instead treat trigger-activ
Power users represent a disproportionately large portion of activity in AI platforms, with their share of total usage growing over time. This trend indicates increasing concentration of AI tool usage
arXiv:2605.28746v1 Announce Type: cross Abstract: This paper studies preference-shaped expected improvement criteria for Bayesian multiobjective optimization. We consider two indicator families which
arXiv:2605.27712v1 Announce Type: new Abstract: Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, P(y=1 mid o_{1
President and Head of AI at Replit, @pirroh is the architect of Replit Agent and former Head of Applied Research at Google X. See him take the stage with @refikanadol on day two of Vibecon. NYC, June
arXiv:2605.27958v1 Announce Type: cross Abstract: Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks
arXiv:2605.28634v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies, yet their adaptation is hindered by data inefficiency an
arXiv:2605.28767v1 Announce Type: new Abstract: Many real-world classification tasks require predicting multiple labels per instance, necessitating the optimization of complex evaluation metrics such
arXiv:2605.28375v1 Announce Type: new Abstract: Prion diseases are rare, rapidly progressive, and fatal neurodegenerative disorders that remain difficult to diagnose, particularly in their early stage
arXiv:2504.12747v2 Announce Type: replace Abstract: The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publi
arXiv:2605.27912v1 Announce Type: cross Abstract: We study efficient differentially private algorithms for estimating monotone statistics, i.e., statistics that are monotone under the addition of new
arXiv:2605.27527v1 Announce Type: cross Abstract: Astrophysical observations taken from Earth are subject to weather, environmental, and scientific constraints that lead to sparse, irregular light cur
arXiv:2602.01745v2 Announce Type: replace-cross Abstract: Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dime
arXiv:2602.22787v2 Announce Type: replace-cross Abstract: Large language model (LLM) hallucinations, meaning fluent but factually incorrect generations, fall into two types: faithfulness violations, w
arXiv:2510.06974v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they may reflect and amplify social biases
arXiv:2605.28231v1 Announce Type: cross Abstract: We present ProgVLA, a compact vision-language-action (VLA) model designed for reliable robot manipulation under tight compute and memory budgets. The
arXiv:2605.27439v1 Announce Type: cross Abstract: AI assistants like ChatGPT and Claude are recommendation engines, not search engines: they answer commercial queries by directly nominating brands rat
arXiv:2605.28360v1 Announce Type: new Abstract: Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a