Knowledge catalogue
arXiv:2606.09590v2 Announce Type: replace Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training t
arXiv:2608.22100v1 Announce Type: new Abstract: Construction robotics and automation offer promising means of improving productivity, alleviating workforce shortages, and reducing workers' exposure to
arXiv:2608.23551v1 Announce Type: cross Abstract: Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existin
arXiv:2608.21821v1 Announce Type: new Abstract: When Wikipedia's language editions describe the same concept, how differently do they frame it? Prior work measures coverage gaps between editions; we m
arXiv:2608.22221v1 Announce Type: new Abstract: We study counterfactual protocol evaluation: whether data collected under a realised observation protocol determine the predictive value of alternatives
arXiv:2608.23391v1 Announce Type: cross Abstract: Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation
arXiv:2608.23390v1 Announce Type: cross Abstract: English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded informat
arXiv:2608.22361v1 Announce Type: cross Abstract: Finite datasets can share the same size and low-order statistics while differing strongly in structural complexity. We connect this dataset complexity
arXiv:2606.18402v2 Announce Type: replace-cross Abstract: Traditional microwave filter design typically relies on iterative parameter tuning and predefined topologies, which limits design space and in
arXiv:2608.22033v1 Announce Type: new Abstract: Stable quadrupedal locomotion on sparse terrain requires selecting state-relevant terrain evidence for precise foot placement. Model-based foothold plan
arXiv:2608.22819v1 Announce Type: new Abstract: Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must si
arXiv:2608.22191v1 Announce Type: new Abstract: Software-engineering agents solve repository-level tasks through long, stochastic tool-use trajectories, and repeated attempts often find fixes missed b
arXiv:2608.23461v1 Announce Type: new Abstract: With rapid advancement over the last few years, many different methods are now widely used for classification. However, training these models requires s
arXiv:2608.21448v1 Announce Type: cross Abstract: DNA methylation provides a stable record of cellular identity, capturing epigenetic programs that distinguish specialized cell states despite a shared
arXiv:2608.22316v1 Announce Type: cross Abstract: Whether an intermediate stage of modern Arabic handwriting helps or hurts historical Arabic HTR is usually decided from one implementation and one com
arXiv:2608.22411v1 Announce Type: new Abstract: Social interaction increasingly takes place in multicultural settings, where individuals may draw on multiple cultural influences and adapt their commun
arXiv:2608.21424v1 Announce Type: new Abstract: Interactive video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified fra
arXiv:2608.21463v1 Announce Type: new Abstract: The study employed an Artificial Neural Network in combination with the optimized Adaptive Moment Estimation (Adam) algorithm, currently the only AQI fo
arXiv:2608.21913v1 Announce Type: new Abstract: Completing dental records from cone-beam computed tomography (CBCT) is difficult when annotation is scarce and individual clinical fields are supported
arXiv:2608.22344v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) achieves state-of-the-art rendering quality at real-time speeds but suffers from 'model bloat' - a large number of redundan
arXiv:2608.23308v1 Announce Type: cross Abstract: An LLM asked for a trading strategy returns three artifacts at once: a natural-language rationale, an executable implementation, and once run, a track
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces a
arXiv:2608.21544v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents, where responses can depend on tool calls and external observations ra
arXiv:2608.21854v1 Announce Type: new Abstract: Weakly supervised video anomaly detectors are trained with video-level labels but are commonly evaluated as temporal localizers using Micro-AUROC or AP
arXiv:2608.22566v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions,
arXiv:2608.21897v1 Announce Type: new Abstract: Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle wi
arXiv:2608.21993v1 Announce Type: new Abstract: We introduce Gated Decoupled Compositional Bandits (GDCB), a family of contextual bandit algorithms with three structural innovations that jointly fall
Mike Scarcella / Reuters: Google launches Gemini Enterprise for Legal, expanding its platform with specialized AI agents and integrations with Thomson Reuters, LexisNexis, and Harvey — Alphabet's Goog
arXiv:2608.23074v1 Announce Type: new Abstract: Vision-language models (VLMs) can answer spatial questions, yet the mechanisms connecting object grounding to spatial reasoning remain poorly understood
arXiv:2608.22485v1 Announce Type: new Abstract: Current visual tokenizers in Multimodal Large Language Models (MLLMs) predominantly rely on patch-based partitioning, which causes severe semantic mixtu
arXiv:2608.22310v1 Announce Type: new Abstract: Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite d
arXiv:2601.12423v2 Announce Type: replace Abstract: Stereo vision between images faces a range of challenges, including occlusions, motion, and camera distortions, across applications in autonomous dr
Cohere’s tweet discusses how someone moved from jailbreaking a PlayStation to becoming CEO of Canada’s leading LLM provider, attributing this career shift to education at the University of Toronto and
arXiv:2606.22342v2 Announce Type: replace Abstract: How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts.
arXiv:2608.23286v1 Announce Type: cross Abstract: Federated learning on non-IID data seeks flat minima to generalize across clients, and existing methods borrow sharpness-aware minimization from centr
arXiv:2608.23566v1 Announce Type: cross Abstract: Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prom
If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured what context compaction actually destroys across 20 product
arXiv:2608.22244v1 Announce Type: cross Abstract: Flow-matching language models refine all token positions in parallel and can trade sampling steps for latency, yet generation quality still degrades s
arXiv:2608.23546v1 Announce Type: cross Abstract: In this paper, we introduce the Inertial Manifold Neural Operator (IMNO) for solving dissipative time-dependent partial differential equations (PDEs).
Introducing ChatGPT Business Premium Seats The new $100 Premium seat is a game changer for small businesses and startups—giving lean teams better tools, faster workflows, and capabilities once reserve
In August 2026, OpenAI released the 'Jalapeño' update, announcing faster response times for ChatGPT and more responsive Codex sessions and agents. The upgrade is designed to provide reliable access as
arXiv:2608.22212v1 Announce Type: cross Abstract: Causal discovery aims to understand the relationships between individual random variables. In many applications, such as brain imaging and climate mod
arXiv:2608.23393v1 Announce Type: cross Abstract: KellyBoost is a single multi-output XGBoost model whose softmax output is the portfolio: with y the vector of per-asset holding-period returns, the tr
arXiv:2608.22506v1 Announce Type: new Abstract: Claim-level Uncertainty Quantification (UQ) aims to mitigate the lack of reliability of Large Language Models (LLMs) by evaluating the factuality of eac
Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. This is an update release, following up from my previous post
arXiv:2606.14782v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with lon
arXiv:2608.21714v1 Announce Type: new Abstract: Recent page-image retrievers such as ColPali have improved retrieval over visually rich documents, yet little is known about how they behave in cross-li
arXiv:2608.21794v1 Announce Type: cross Abstract: GUI grounding evaluations that expose UI elements as text metadata often treat high instruction-element embedding similarity as evidence of semantic g
arXiv:2607.16327v2 Announce Type: replace Abstract: Medical image segmentation is essential for modern computer-aided medicine. Recently, text-guided segmentation has shown promise by incorporating cl
arXiv:2608.22465v1 Announce Type: new Abstract: High-fidelity free-viewpoint video (FVV) and interactive rendering increasingly rely on explicit Gaussian representations, yet practical deployment rema
arXiv:2509.20067v5 Announce Type: replace Abstract: Large language models (LLMs) have shown promise in supporting medical diagnosis, with prompting-based methods offering a flexible and deployable mea
arXiv:2608.22167v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks
arXiv:2509.23705v2 Announce Type: replace Abstract: Multi-robot coverage path planning commonly balances geometric area or path length under a constantspeed assumption. This assumption is inadequate w
arXiv:2608.23397v1 Announce Type: new Abstract: Interactive clinical agents must gather decisive evidence and convert it into grounded actions under partial observability. A correct final diagnosis al
arXiv:2608.22137v1 Announce Type: new Abstract: Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterpris
arXiv:2608.21867v1 Announce Type: new Abstract: LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering,
arXiv:2608.22061v1 Announce Type: new Abstract: Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and the
arXiv:2608.22149v1 Announce Type: cross Abstract: LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedie
arXiv:2608.23497v1 Announce Type: new Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with
arXiv:2608.22196v1 Announce Type: cross Abstract: While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during separ