Knowledge catalogue
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
arXiv:2605.28066v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face significant bottle
arXiv:2605.28058v1 Announce Type: new Abstract: Recent work explored the capabilities of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA) through few-shot prompting, requiring su
arXiv:2605.27594v1 Announce Type: cross Abstract: We study the problem of computationally efficient proper agnostic learning of multidimensional concept classes under the Gaussian distribution. In thi
arXiv:2605.28230v1 Announce Type: new Abstract: Modern video generative models produce visually impressive results, yet frequently violate basic physical principles. We propose Proprio, a training-fre
arXiv:2605.28293v1 Announce Type: cross Abstract: Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinf
arXiv:2605.28172v1 Announce Type: new Abstract: In safety-critical robotics applications, guaranteed and practical uncertainty quantification (UQ) in perception is vital. Many existing works either of
arXiv:2605.28487v1 Announce Type: new Abstract: Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten sy
arXiv:2605.28283v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) dominate the parameter count and computation of modern language models, yet existing pruning methods often struggle to co
arXiv:2605.28207v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory,
arXiv:2605.28363v1 Announce Type: new Abstract: Causal relation extraction (CRE) is central to biomedical text mining, but current resources often conflate causal relations with broader associations,
arXiv:2602.15894v2 Announce Type: replace Abstract: In many large language model (LLM) alignment applications, users expect not only high-quality outputs but also substantial diversity. However, exist
arXiv:2605.27417v1 Announce Type: cross Abstract: With the advent of sixth-generation (6G) mobile communication technology, vehicle-to-everything (V2X) communication faces unprecedented challenges in
arXiv:2605.27942v1 Announce Type: cross Abstract: Principal component analysis (PCA) is traditionally implemented through a covariance or kernel matrix, leading-eigenvector extraction, and hard rank-k
arXiv:2605.28166v1 Announce Type: cross Abstract: Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling. Existing approaches typ
arXiv:2605.28091v1 Announce Type: new Abstract: Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple
📢Qwen3.7-Max just hit #3 on ITbench-AA — a fresh benchmark testing how well models handle real-world enterprise IT tasks, agentic-style. 🔧Agentic era, go with Qwen.🏃🏃 Artificial Analysis and IBM Resea