Knowledge catalogue
arXiv:2502.11008v2 Announce Type: replace Abstract: Counterfactual reasoning is widely recognized as one of the most challenging and intricate aspects of causality in artificial intelligence. In this
arXiv:2604.10039v1 Announce Type: new Abstract: Vision--language models (VLMs) have achieved impressive performance on complex multimodal reasoning tasks, yet they still fail on simple grounding skill
arXiv:2506.18438v2 Announce Type: replace Abstract: Editing natural images using textual descriptions in text-to-image diffusion models remains a significant challenge, particularly in achieving consi
arXiv:2512.21877v3 Announce Type: replace-cross Abstract: Cricket is the second most popular sport worldwide, with billions of fans seeking advanced statistical insights unavailable through standard w
arXiv:2604.10054v1 Announce Type: new Abstract: This study addresses a key limitation in deep learning Automatic Modulation Classification (AMC) models, which perform well at high signal-to-noise rati
Cybersecurity Looks Like Proof of Work Now The UK's AI Safety Institute recently published Our evaluation of Claude Mythos Preview’s cyber capabilities, their own independent analysis of Claude Mythos
arXiv:2604.11007v1 Announce Type: new Abstract: Semantic segmentation of 3D point cloud scenes is a crucial task for various applications. In real-world scenarios, training segmentation models often f
datasette PR #2689: Replace token-based CSRF with Sec-Fetch-Site header protection Datasette has long protected against CSRF attacks using CSRF tokens, implemented using my asgi-csrf Python library. T
arXiv:2604.11119v1 Announce Type: cross Abstract: This paper reorganizes the current manuscript around the DPO versus DDO-RM preference-optimization project and focuses on two parts: the algorithmic v
arXiv:2604.10288v1 Announce Type: new Abstract: This essay identifies a failure mode of AI chat systems that we term attribution laundering: the model performs substantive cognitive work and then rhet
arXiv:2603.23916v2 Announce Type: replace-cross Abstract: Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues for forensics and security. In these high-sta
arXiv:2603.27383v2 Announce Type: replace Abstract: Parameter Recombination (PR) methods aim to efficiently compose the weights of a neural network for applications like Parameter-Efficient FineTuning
arXiv:2604.11581v1 Announce Type: new Abstract: LLM evaluations drive which models get deployed, which safety standards get adopted, and which research conclusions get published. Yet these scores carr
🚀 deepagents 0.5 release 👉 Async subagents - kick off background tasks on any Agent Protocol backed server while you continue to interact with the main agent. Start multiple background tasks in parall
arXiv:2604.09590v1 Announce Type: new Abstract: Automated peer review is often framed as generating fluent critique, yet reviewers and area chairs need judgments they can audit: where a concern applie
arXiv:2604.10102v1 Announce Type: cross Abstract: AI-generated image detectors suffer significant performance degradation under real-world image corruptions such as JPEG compression, Gaussian blur, an
arXiv:2509.05342v3 Announce Type: replace Abstract: We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image
arXiv:2604.09596v1 Announce Type: new Abstract: Dermatologic diseases impose a large and growing global burden, affecting billions and substantially reducing quality of life. While modern therapies ca
arXiv:2510.09389v2 Announce Type: replace-cross Abstract: Deep sequence models, ranging from Transformers and State Space Models (SSMs) to more recent approaches such as gated linear RNNs, fundamental
arXiv:2604.09644v1 Announce Type: cross Abstract: Corporate AI-washing-the strategic misrepresentation of AI capabilities via exaggerated or fabricated cross-channel disclosures-has emerged as a syste
arXiv:2404.18905v3 Announce Type: replace-cross Abstract: Randomized trials are considered the gold standard for making informed decisions in medicine, yet they often lack generalizability to the pati
arXiv:2604.11806v1 Announce Type: new Abstract: To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare, complex,
arXiv:2604.11171v1 Announce Type: new Abstract: Computer-aided detection (CADe) of early neoplasia in Barrett's esophagus is a low-prevalence surveillance problem in which clinically relevant findings
arXiv:2604.10819v1 Announce Type: cross Abstract: A recent line of work initiated by Chiesa and Gur and further developed by Herman and Rothblum investigates the sample and communication complexity of
arXiv:2604.10425v1 Announce Type: new Abstract: Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain rem
arXiv:2507.03336v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly tasked with invoking enterprise APIs, yet they routinely falter when near-duplicate tools vie for the
arXiv:2601.14346v2 Announce Type: replace-cross Abstract: Accurate prediction of drug response in precision medicine requires models that capture how specific chemical substructures interact with cell
arXiv:2604.11088v1 Announce Type: new Abstract: Developers increasingly guide AI coding agents through natural language instruction files (e.g., CLAUDE.md, .cursorrules), yet no controlled study has m
arXiv:2604.10690v1 Announce Type: new Abstract: Foundation models have shown remarkable performance across diverse tasks, yet their ability to construct internal spatial world models for reasoning and
arXiv:2604.11177v1 Announce Type: new Abstract: We benchmark how internal reasoning traces, which we call thought streams, affect video scene understanding in vision-language models. Using four config
arXiv:2604.09666v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reason
arXiv:2601.03926v2 Announce Type: replace Abstract: The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined poli
arXiv:2604.10077v1 Announce Type: new Abstract: In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent d
arXiv:2604.07389v2 Announce Type: replace Abstract: Crime pattern analysis is critical for law enforcement and predictive policing, yet the surge in criminal activities from rapid urbanization creates
arXiv:2511.11232v2 Announce Type: replace Abstract: Constructing a unified 3D scene understanding model has long been hindered by the significant topological discrepancies across different sensor moda
arXiv:2512.00375v2 Announce Type: replace Abstract: Existing motion planning methods often struggle with rapid-motion obstacles due to an insufficient understanding of environmental changes. To addres
arXiv:2604.11094v1 Announce Type: cross Abstract: Contemporary microservice systems continue to grow in scale and complexity, leading to increasingly frequent and costly failures. While recent LLM-bas
arXiv:2604.11400v1 Announce Type: cross Abstract: High-speed autonomous racing presents extreme perception challenges, including large relative velocities and substantial domain shifts from convention
arXiv:2604.11512v1 Announce Type: cross Abstract: The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fun
arXiv:2603.05463v2 Announce Type: replace Abstract: Single-object tracking (SOT) on edge devices is a critical computer vision task, requiring accurate and continuous target localization across video
arXiv:2604.10200v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric eva
arXiv:2604.05005v2 Announce Type: replace-cross Abstract: Large language models are increasingly used as educational assistants, yet evaluation of their educational capabilities remains concentrated o
arXiv:2511.18957v2 Announce Type: replace Abstract: Video virtual try-on technology provides a cost-effective solution for creating marketing videos in fashion e-commerce. However, its practical adopt
arXiv:2604.11038v1 Announce Type: new Abstract: We present EgoFun3D, a coordinated task formulation, dataset, and benchmark for modeling interactive 3D objects from egocentric videos. Interactive obje
arXiv:2604.11547v1 Announce Type: cross Abstract: While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning dat
arXiv:2604.11174v1 Announce Type: cross Abstract: Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluatio
arXiv:2604.10117v1 Announce Type: new Abstract: Photoplethysmography (PPG)-based blood pressure (BP) estimation is a challenging task, particularly on resource-constrained wearable devices. However, f
arXiv:2601.04392v2 Announce Type: replace-cross Abstract: This paper introduces a fuzzy reinforcement learning framework, Enhanced-FQL(lambda), that integrates novel Fuzzified Eligibility Traces (FET)
arXiv:2604.11299v1 Announce Type: cross Abstract: In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the e
arXiv:2604.11154v1 Announce Type: new Abstract: New multi-modal large language models (MLLMs) are continuously being trained and deployed, following rapid development cycles. This generative AI frenzy
ERNIE Image is an open-source text-to-image generation model developed by Baidu, built on a single-stream Diffusion Transformer (DiT) paired with a lightweight Prompt Enhancer that expands brief user
arXiv:2604.11462v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle with long-horizon tasks due to the 'context bottleneck' and the 'lost-in-the-middle' phenomenon, where accumulated
arXiv:2604.11182v1 Announce Type: new Abstract: Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benc
arXiv:2604.09606v1 Announce Type: new Abstract: Traditional benchmarks for large language models (LLMs), such as HELM and AIR-BENCH, primarily assess safety risk through breadth-oriented evaluation ac
arXiv:2604.09698v1 Announce Type: cross Abstract: The growing ubiquity of Extended Reality (XR) is driving Conversational Recommendation Systems (CRS) toward visually immersive experiences. We formali
arXiv:2604.10535v1 Announce Type: cross Abstract: Incorporating large language models (LLMs) in medical question answering demands more than high average accuracy: a model that returns substantively d
arXiv:2604.10894v1 Announce Type: new Abstract: Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references.
arXiv:2604.09568v1 Announce Type: cross Abstract: High-fidelity diagram creation requires the complex orchestration of semantic topology, visual styling, and spatial layout, posing a significant chall
Excited to be part of @ollama Gemma Day tomorrow in Palo Alto! Khoa Pham (@kwafam7) from @radixark will demo Gemma 4 in production with SGLang 🚀 Come say hi! 📷 RSVP: https://luma.com/ollama-gemma4 Oll
arXiv:2604.09741v1 Announce Type: cross Abstract: For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed age