Knowledge catalogue
arXiv:2608.01077v1 Announce Type: new Abstract: Referring expression segmentation requires language conditioned localization and pixel-accurate masks, but monolithic models can be costly to deploy. We
arXiv:2608.01470v1 Announce Type: new Abstract: Event cameras produce sparse and asynchronous event streams that provide rich spatio-temporal information for efficient perception. Recent advances in e
arXiv:2608.00094v1 Announce Type: new Abstract: Pretrained video diffusion models can act as renderers when the desired scene state is already specified by an animated mesh, a camera trajectory, and a
arXiv:2601.05713v2 Announce Type: replace Abstract: Understanding how large language models (LLMs) represent natural language is a central challenge in natural language processing (NLP) research. Many
arXiv:2608.01028v1 Announce Type: new Abstract: Deploying Vision-Language-Action (VLA) robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical ad
arXiv:2608.00072v1 Announce Type: new Abstract: Recent advances in quantum computing are opening new possibilities for Earth Observation (EO) data analysis. Quantum machine learning (QML) approaches o
arXiv:2608.02598v1 Announce Type: new Abstract: Aerial-ground person re-identification is a challenging task due to cross-platform viewpoint variations, which cause severe occlusion and geometric defo
arXiv:2608.01035v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is sev
arXiv:2608.02430v1 Announce Type: cross Abstract: We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth
We were proud to host “Build with Frontier Intelligence,” http://Z.ai ’s first community meetup, together with @AISingapore, at Tencent’s venue. During the event, http://Z.ai shared insights into the
arXiv:2608.01851v1 Announce Type: new Abstract: Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that w
We're detailing two new incidents that occurred during external cyber evaluations conducted by independent evaluation partners. We outline what happened, how the activity was contained, and how we’re
arXiv:2607.17017v2 Announce Type: replace-cross Abstract: As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources
arXiv:2608.00105v1 Announce Type: new Abstract: Pathology foundation models are reported to encode molecular programmes in tissue morphology, but the evidence is usually a cohort-wide ranked gene list
arXiv:2608.01042v1 Announce Type: cross Abstract: Enterprise AI agents act across many apps whose data changes continuously, so an answer is correct only relative to what data existed and who could se
arXiv:2603.06591v2 Announce Type: replace-cross Abstract: Transformers frequently allocate disproportionate attention to specific tokens, a phenomenon known as attention sinks. Causal large language m
arXiv:2608.00013v1 Announce Type: new Abstract: Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fu
arXiv:2608.01085v1 Announce Type: cross Abstract: LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduce
arXiv:2603.19040v2 Announce Type: replace Abstract: Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questi
arXiv:2608.01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward. Here, a trajecto
arXiv:2608.01720v1 Announce Type: new Abstract: Extremely low-light RAW enhancement aims to recover severely attenuated sensor signals, yet existing methods often focus on illumination and noise while
Its been over a week after kimi k3 open weights dropped , and the hype seems to have dropped , everyone is behind dsv4 now. Now seems to be a good time to remove the extra usage credits criteria for K
arXiv:2601.19913v4 Announce Type: replace Abstract: LLMs now help students plan, draft, and revise essays. Educational assessment therefore faces a basic question: how should student and LLM writing b
arXiv:2608.01378v1 Announce Type: new Abstract: Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensi
arXiv:2608.01602v1 Announce Type: new Abstract: Cardiac digital twins convert clinical images into physiological measurements through observation operators, yet calibration studies often assume a fixe
arXiv:2603.17445v5 Announce Type: replace-cross Abstract: When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable?
arXiv:2608.00747v1 Announce Type: new Abstract: Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to pr
arXiv:2608.01428v1 Announce Type: cross Abstract: Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call
arXiv:2608.01409v1 Announce Type: new Abstract: Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted, or unaddressed: they should also produce evidence
arXiv:2608.01176v1 Announce Type: new Abstract: Political polarization has become a defining feature of online discourse, yet its long-term evolution remains poorly understood. We present a longitudin
arXiv:2608.00410v1 Announce Type: cross Abstract: Human language is highly polysemous. Many common words (e.g., 'bank' or 'palm') carry several distinct meanings that shape what humans communicate and
arXiv:2608.00626v1 Announce Type: new Abstract: The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface. This assumpti
arXiv:2608.00076v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text. W
arXiv:2608.01004v1 Announce Type: new Abstract: Platform teams hosting agent-extensibility surfaces face a regression-economics paradox: every onboarding customer ships an evaluation set tuned to thei
arXiv:2504.20477v4 Announce Type: replace Abstract: Robotic systems increasingly operate in dynamic, unpredictable environments, where tightly coupled sensors and software modules increase the probabi
arXiv:2608.02551v1 Announce Type: cross Abstract: Fairness evaluation concerns not only what a model produces, but also what its outputs ought to be compared against. When a model generates 'a CEO in
I use A LOT both openAI and Anthropic products. When I need some frontend work (pure web dev) (or answer that feel less verbose and more to the point) I use Anthropic. For multimodality openAI feels b
It's more accurate to say that many highly engaged online gamers are hostile to AI, not that 'gamers' as a whole are. Gaming is a huge community with hundreds of millions of people, and opinions vary
arXiv:2608.02547v1 Announce Type: new Abstract: Action chunking---predicting and executing multiple actions instead of a single action---has proven to be a critical component for learning effective ro
arXiv:2608.01388v1 Announce Type: cross Abstract: Runtime safety monitors based on Linear Temporal Logic (LTL) and finite automata (FSA) are increasingly deployed to intercept unsafe tool-call sequenc
arXiv:2608.02412v1 Announce Type: new Abstract: Large language models (LLMs) have become the default tool for a remarkable range of tasks, yet they have had conspicuously little success at one of the
arXiv:2608.01017v1 Announce Type: new Abstract: A language model that abandons a correct medical answer under user pushback is more dangerous than one that was simply wrong, because it lends the credi
arXiv:2608.00642v1 Announce Type: new Abstract: Recently, Wi-Fi sensing has played a significant role in Human Activity Recognition (HAR), as it enables the detection of various activities using only
arXiv:2608.01880v1 Announce Type: new Abstract: World Action Models generate fixed-horizon action chunks through iterative denoising, creating substantial inference latency that can cause pauses, stal
arXiv:2608.01845v1 Announce Type: cross Abstract: Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse
arXiv:2608.02603v1 Announce Type: new Abstract: Controllable video generation models are increasingly being developed as world models. Accordingly, evaluating them in this role extends beyond the appa
arXiv:2510.10726v2 Announce Type: replace Abstract: We present WorldMirror, a unified feed-forward model for comprehensive 3D geometric prediction tasks. Unlike existing methods constrained to image-o
arXiv:2608.00582v1 Announce Type: new Abstract: Pretrained byte-level BPE tokenizers can segment underrepresented languages inefficiently. Replacing a tokenizer changes the meaning of nearly every tok
arXiv:2608.00036v1 Announce Type: new Abstract: Real-world document tasks often ask professionals to answer questions from annual reports, regulations, clinical guidelines, and technical manuals that
arXiv:2608.00935v1 Announce Type: new Abstract: Electronic Health Records (EHRs) are widely used for clinical risk prediction using machine learning. International Classification of Diseases (ICD) cod
arXiv:2603.28568v2 Announce Type: replace Abstract: Vision-language models (VLMs) share visual-textual representations across zero-shot classification, image captioning, and visual question answering
arXiv:2608.02271v1 Announce Type: new Abstract: Parameter-Efficient Fine-tuned (PEFT) models are frequently downloaded from open repositories by practitioners. This widespread practice creates a signi
arXiv:2608.00544v1 Announce Type: new Abstract: Identifying the ``Inflamed'' immunophenotype in Gastric Adenocarcinoma predicts immunotherapy response but requires an expensive 10-gene RNA signature.
arXiv:2607.19335v2 Announce Type: replace-cross Abstract: Controlling the Lipschitz constant of a neural network is a standard way to promote robustness and stability. Most existing constraining strat
been thinking about how the desktop 70-class has sat at 12GB for two generations now, 4070, 4070 super, 5070, all 12GB. the 1070 gave you 8GB back in 2016 and it felt generous for the price. ten years
Horiyuki 'horiyuki42' joined Sakana AI Labs in August 2026 as an Applied Research Engineer Intern. He plans to work full‑time during the university summer recess while concentrating on large‑language‑
arXiv:2605.06340v2 Announce Type: replace-cross Abstract: Continuous post-deployment compliance audits, mandated by emerging regulations such as the EU AI Act and Digital Services Act, create a class
arXiv:2607.28944v1 Announce Type: cross Abstract: Student engagement (SE) is a critical predictor of academic performance and retention in STEM education, yet existing measurement approaches are often
Zvi Mowshowitz / Don't Worry About the Vase: A detailed recap of the real-world target hacks by OpenAI and Anthropic models, exposing failures in AI alignment training and lack of meaningful supervisi
arXiv:2607.29122v1 Announce Type: new Abstract: Pixel-space diffusion models aim to learn an end-to-end generator directly over raw pixels. This is challenging because a single model must capture both