Knowledge catalogue
arXiv:2606.30512v1 Announce Type: cross Abstract: Why overparameterised deep networks generalise so remarkably well remains one of the most stubborn open questions in machine learning theory. Classica
arXiv:2606.30252v1 Announce Type: new Abstract: Inoculation prompting is a selective generalization technique used against Emergent Misalignment. We introduce inoculation adapters (IA), which similarl
arXiv:2512.17504v2 Announce Type: replace-cross Abstract: Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) rema
Genebench-Pro appears to be a case study or tool from OpenAI focused on benchmarking or evaluating genetic/genomic analysis capabilities, likely demonstrating how OpenAI's models or tools can be appli
arXiv:2606.28333v1 Announce Type: cross Abstract: egin{quote} The biases in Large Language Models' (LLMs) outputs remain inadequately theorised, particularly from the perspective of the Global South.
arXiv:2405.01906v3 Announce Type: replace Abstract: In modern intelligent transportation systems (ITS), particularly in freight transportation and logistics, real-time route planning is crucial. It pr
arXiv:2511.14540v2 Announce Type: replace Abstract: This paper focuses on a challenging setting of simultaneously modeling geometry and appearance of hand-object interaction scenes without any object
arXiv:2603.13082v2 Announce Type: replace Abstract: Text-guided 3D motion editing has seen success in single-person scenarios, but its extension to multi-person settings is less explored due to limite
arXiv:2606.30262v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models often fail to faithfully render explicit textual descriptions, instead defaulting to strongly learned visual priors
arXiv:2606.30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated. We ask wh
arXiv:2604.02371v2 Announce Type: replace-cross Abstract: Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have n
arXiv:2409.00743v4 Announce Type: replace-cross Abstract: In recent years, much of the research on clustering algorithms has primarily focused on enhancing their accuracy and efficiency, frequently at
arXiv:2606.29459v1 Announce Type: cross Abstract: Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine
arXiv:2606.29386v1 Announce Type: new Abstract: Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series ext
Editor’s note: This post is part of Into the Omniverse, a series focused on how developers, 3D practitioners, and enterprises can transform their workflows using the latest advances in OpenUSD and NVI
Today, we’re excited to announce the availability of Anthropic’s most advanced Sonnet model, Claude Sonnet 5, on Amazon Bedrock and Claude Platform on AWS. Claude Sonnet 5 is the first Sonnet model of
GeneBench-Pro is a comprehensive benchmarking tool or dataset introduced by OpenAI designed to evaluate AI model performance on genomic and gene-related tasks. It likely provides standardized metrics
Introducing SWE-Together: a multi-turn benchmark built from real user–agent coding sessions. Coding agents are often benchmarked like exam-takers: given the full spec up front, then graded on the fina
TabFM is a foundation model designed for tabular data classification and regression that eliminates the need for manual model training, hyperparameter tuning, and complex feature engineering by framin
Vercel Container Registry (VCR) is a new container image registry service introduced by Vercel for storing and managing Docker container images. This offering enables developers to host and deploy con
arXiv:2606.29164v1 Announce Type: cross Abstract: Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains
arXiv:2512.11095v2 Announce Type: replace Abstract: Label ambiguity is an inherent and largely unaddressed challenge in real-world electrocardiogram (ECG) diagnosis, arising from overlapping condition
arXiv:2509.13873v3 Announce Type: replace Abstract: Pelvic fractures pose significant diagnostic challenges, particularly in cases where fracture signs are subtle or invisible on standard radiographs.
arXiv:2606.29880v1 Announce Type: new Abstract: Customized Portrait Generation (CPG) technologies have been widely used to generate high-fidelity person images given an input image indicating the iden
arXiv:2606.28456v1 Announce Type: cross Abstract: LLMs agents are increasingly used in multi-agent settings, yet their behaviour in sustainability games remains largely unexplored. This work investiga
Muon optimizer shows faster training speeds compared to traditional optimizers, but analysis reveals it sacrifices the simplicity bias that older optimizers maintain, potentially impacting model gener
arXiv:2505.20935v3 Announce Type: replace Abstract: Recent open-weight text-to-image (T2I) diffusion models still struggle with multi-instance prompts, often omitting or merging instances and mixing s
arXiv:2606.27944v1 Announce Type: cross Abstract: Phone-use Agents can execute complex tasks end to end across real mobile applications. By operating a real device on the user's behalf, they reach far
it's a sad day when we stop learning. nothing quite replicates the pace and structure of college, but Independent Studies has become my version of continuing education post-grad. some of my favorite c
Sebastian Raschka announced the availability of a book through Manning Publications (with immediate shipping) and Amazon (available for preorder with delivery in a few weeks). The specific book title
It's not just the Lutnick sons cashing in on the Trump family's White House self-dealing. World Liberty Financial — the crypto venture Don Jr. & Eric launched with Steve Witkoff's sons, Zach & Alex —
It's wild how quickly Etched designed and got the chips out, all within 2 years. They went deep, hardcoding attention into silicon and getting very high MFU. This kind of hardware tailored made for LL
arXiv:2606.30523v1 Announce Type: new Abstract: Covariance matrices serve as compact descriptors of feature distributions in many machine-learning pipelines, including domain adaptation and Gaussian e
I've added video support to my 'shot-scraper' browser automation tool - you (or your coding agent) can now create a storyboard YAML file and use that to record a video demo of new web application feat
arXiv:2606.28712v1 Announce Type: cross Abstract: Classical SLAM estimates metric poses and a geometric map but produces no actionable predictive model for planning. Action-conditioned world models le
arXiv:2606.28395v1 Announce Type: new Abstract: Recent studies have shown that spatial properties of tumors are critical for understanding disease biology and predicting patient outcomes. These spatia
joined @LangChain almost three months ago and have spent a ton of time thinking about evals! i think that harbor is the future of eval frameworks so really enjoyed being able to bring it into tighter
arXiv:2603.06829v2 Announce Type: replace Abstract: Subsurface ore detection is of paramount importance given the rising depletion of shallow mineral resources in recent years. It is crucial to explor
arXiv:2603.06168v3 Announce Type: replace Abstract: Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarcit
arXiv:2606.16776v2 Announce Type: replace Abstract: Generalist robot policies require trustworthy evaluation and robot-usable training data, but both are difficult to scale with physical robots alone.
Just hardcore engineering This required: - advanced optics solutions to be able to see vessels through an opaque layer of tissue - precision manufacturing to machine micrometer scale features in our n
This post from Swyx discusses San Francisco-specific phenomena and features commentary from the 'Orc-estrator' and @swyx, likely relating to AI/engineering topics given the hashtags #aiewf (AI Enginee
arXiv:2606.28421v1 Announce Type: cross Abstract: Text-to-image (T2I) diffusion models typically require substantial computational resources and cloud infrastructure, posing significant challenges for
arXiv:2606.29863v1 Announce Type: new Abstract: Agentic search equips large language models with dynamic retrieval abilities, but existing reinforcement learning methods remain limited by reward spars
arXiv:2606.28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, model
arXiv:2606.29028v1 Announce Type: new Abstract: Keypose-based manipulation decomposes tasks into critical waypoints to simplify policy learning for long-horizon tasks, but existing approaches rely on
arXiv:2606.28568v1 Announce Type: new Abstract: Speech-driven 3D facial animation methods face significant challenges in simultaneously achieving high-fidelity motion and precise artistic control at p
arXiv:2606.29959v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows th
arXiv:2601.21864v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing metho
arXiv:2606.29119v1 Announce Type: cross Abstract: We introduce a pre-registered screening rule that decides, before any implementation, whether an evolutionary / population / lifecycle outer loop over
arXiv:2606.30258v1 Announce Type: cross Abstract: Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Ye
arXiv:2606.29628v1 Announce Type: cross Abstract: In this paper, two novel data-driven models based on kriging and neural networks (NN) are proposed to predict pressure losses across perforated plates
arXiv:2606.29243v1 Announce Type: new Abstract: We present KrishokChat, the first citation-grounded Bengali agricultural instruction-tuning dataset for crop advisory in low-resource settings. We estab
arXiv:2606.30243v1 Announce Type: new Abstract: This paper presents KYON, a hybrid wheel-legged quadruped robot equipped with a bimanual upper body for loco-manipulation tasks. The platform features a
arXiv:2606.29374v1 Announce Type: new Abstract: High-fidelity reconstruction of dynamic urban environments is a cornerstone of autonomous driving simulation and large-scale world modeling. While 3D Ga
arXiv:2606.28823v1 Announce Type: new Abstract: Recent large language models (LLMs) achieve strong performance on entity matching without requiring task-specific training data. However, applying these
arXiv:2511.21256v2 Announce Type: replace Abstract: Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety
arXiv:2606.28841v1 Announce Type: cross Abstract: Large language models are increasingly capable of mathematical reasoning, but the proofs they generate are often unreliable and hard to verify. Intera
arXiv:2606.29358v1 Announce Type: new Abstract: Multi-robot manipulation requires jointly reasoning about contact formations, robot motions under coupled dynamics, and collision avoidance. Systematica
LangChain 今天连发两记，直接把 agent reliability 往前推了一步：一套统一评估栈，一个不用完整沙箱的代码执行方案。 先说评估。长运行、有状态的 agent 怎么测？Harbor + LangSmith 的组合给出一个 runner，能挂载 sandbox、接入 observability，终于不是靠单元测试糊弄了。 再看代码执行。Deep Agents 需要跑不受信代码，