Knowledge catalogue
arXiv:2606.23689v1 Announce Type: cross Abstract: Learning robust dexterous grasping requires real-world data that records the physical outcomes of grasp attempts. Such data is hard to obtain at scale
Available today: the API, Document AI in Mistral AI Studio, Amazon SageMaker, Microsoft Foundry, coming soon Snowflake Parse Document, or self-hosted on a single container, so your documents never lea
arXiv:2606.22188v1 Announce Type: new Abstract: Large multi-modal language models are increasingly deployed in high-stakes domains, making well-calibrated uncertainty essential. Traditional Bayesian m
arXiv:2606.20909v1 Announce Type: new Abstract: Earth observation imagery plays a critical role in environmental monitoring, urban planning, disaster assessment, and climate analysis. While multi-spec
arXiv:2606.20668v1 Announce Type: cross Abstract: LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI appli
arXiv:2606.22338v1 Announce Type: cross Abstract: Robots deployed in realistic settings will accumulate experience across many sessions and tasks over their deployment. The robot's tasks may often req
arXiv:2606.22497v1 Announce Type: new Abstract: Microscopic imaging provides essential visual evidence for studying plant biology and pathology at the cellular and subcellular levels. However, existin
arXiv:2606.15127v2 Announce Type: replace Abstract: Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students inte
arXiv:2606.20599v1 Announce Type: cross Abstract: Tree of Thought (ToT) search has become a promising direction for improving the reasoning capabilities of large language models, but deploying these m
arXiv:2606.20770v1 Announce Type: cross Abstract: Current Vision-Language Models (VLMs) are celebrated for their multilingual capabilities, yet they operate under a flawed assumption: that one languag
arXiv:2505.24160v3 Announce Type: replace-cross Abstract: Medical image challenges have played a transformative role in advancing the field, catalyzing innovation and establishing new performance benc
arXiv:2511.22973v2 Announce Type: replace Abstract: Long video generation is a critical step toward building realistic world models, requiring both high visual fidelity and long-range interaction cons
arXiv:2606.22999v1 Announce Type: new Abstract: The rapid deployment of Vision-Language Models (VLMs) in dynamic environments necessitates the ability to learn continuously without forgetting. However
arXiv:2606.22824v1 Announce Type: new Abstract: Speech-to-IPA transcription is useful when the desired output is pronunciation rather than orthographic text, but competitive multilingual systems are o
Bring open models to where you're already working. FireConnect brings Fireworks' top models directly into Claude Code, Pi, OpenCode, and Codex. Watch our Head of AI Education @Prof_oz show you how: Ho
arXiv:2606.18429v2 Announce Type: replace Abstract: Accurately aligning CAD models to their corresponding objects in indoor RGB-D scans is a central challenge in 3D semantic reconstruction. The task r
arXiv:2606.21949v1 Announce Type: new Abstract: Accurate and comprehensive video captions with consistent subject references are critical for downstream understanding and generation tasks. However, fe
arXiv:2606.22699v1 Announce Type: new Abstract: Frontier multimodal models can guess whether a person is lying from a testimony video. To do so, they stream that raw face and voice to a third-party mo
arXiv:2606.20715v1 Announce Type: new Abstract: Micro-expression recognition (MER) in realistic scenarios demands high temporal sensitivity and ecological validity, yet existing benchmarks are largely
arXiv:2606.22000v1 Announce Type: cross Abstract: We introduce CFAgentBench, a reproducible, self-hostable environment and benchmark for autonomous construction-finance agents: a CFO/controller-class
arXiv:2606.22862v1 Announce Type: new Abstract: Forced chain-of-thought (CoT) is widely assumed to make vision-language models more reliable on video question answering. We propose a small three-probe
arXiv:2606.21657v1 Announce Type: new Abstract: Facial expressions are nonverbal social signals used in human interaction, but facial expression recognition datasets often focus on static images, basi
arXiv:2606.21109v1 Announce Type: new Abstract: Virtual-cell and perturbation models are increasingly used to predict cellular responses for biomedical discovery, but chemical and genetic perturbation
arXiv:2606.21020v1 Announce Type: new Abstract: The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visua
arXiv:2606.21146v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization
Claude is really proactive with Claude Tag. You don’t need to prompt it to do work, it can do work proactively based on your instructions. It has excellent memory and access to your data, so it can be
Claude Tag is an incredible new form factor for agents, so I think it's going to take some time to figure out the best practices, but these are some of my favorites 🧵 Introducing Claude Tag, a new way
arXiv:2606.22669v1 Announce Type: new Abstract: Adaptive stochastic convex optimization (SCO) methods face a fundamental ``price of adaptivity'' barrier: under the standard set of assumptions, they ca
arXiv:2606.22026v1 Announce Type: new Abstract: Machine learning systems deployed in dynamic environments frequently operate under nonstationary data distributions, where controlled distribution shift
arXiv:2603.10757v2 Announce Type: replace Abstract: When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual
arXiv:2606.21230v1 Announce Type: new Abstract: Wound rotor synchronous motors have emerged as a strong alternative that eliminates dependence on REEs. However, WRSM design requires the simultaneous o
arXiv:2606.22567v1 Announce Type: new Abstract: Few-shot prompt learning is an effective strategy for adapting CLIP to downstream tasks, but class-only prompt optimization can overfit base-class super
arXiv:2606.22659v1 Announce Type: cross Abstract: Prompt-injection detectors are deployed as guards: a model scores an input and a downstream system trusts or blocks it on that score. I study the conf
arXiv:2606.21116v1 Announce Type: new Abstract: Proofreading--correcting segmentation errors in 3D brain reconstructions--is the rate-limiting step in synapse-resolution connectomics. We release Conne
arXiv:2606.21935v1 Announce Type: new Abstract: Diffusion models excel at capturing multi-modal action distributions in robot imitation learning. However, in multi-task and long-horizon scenarios, mon
arXiv:2606.21932v1 Announce Type: new Abstract: Remote sensing change detection (CD) from bi-temporal imagery is critical for applications such as urban monitoring, disaster assessment, and environmen
arXiv:2606.20608v1 Announce Type: cross Abstract: Generative text-to-video systems can produce visually fluent educational clips, but they rarely encode the pedagogical content knowledge (PCK) needed
arXiv:2606.20376v2 Announce Type: replace Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While bench
arXiv:2606.22317v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward continuously improving large language models. Recent w
arXiv:2606.22439v1 Announce Type: new Abstract: Commercial greenhouse cucumber production is graded by fruit length, which drives harvest scheduling, labour allocation, and logistics. Manual measureme
arXiv:2606.22476v1 Announce Type: new Abstract: Humans can effortlessly reason about scenes across different viewpoints, yet it remains unclear whether Vision-Language Models (VLMs) possess similar cr
arXiv:2606.21916v1 Announce Type: new Abstract: The performance of deep learning models is affected by not only data quantity but also data quality. Data pruning is a process by which practitioners ca
arXiv:2606.21337v1 Announce Type: new Abstract: Massive unstructured multimodal streams suffer from high 'data entropy,' impeding both efficient human knowledge acquisition and high-quality AI post-tr
arXiv:2606.21496v1 Announce Type: cross Abstract: Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-spe
arXiv:2606.22494v1 Announce Type: cross Abstract: Sign language is a primary mode of communication for the global deaf and hard-of-hearing community, yet automated tools that recognize sign gestures f
arXiv:2606.21023v1 Announce Type: new Abstract: As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict syst
This Vercel changelog entry describes integration between Claude Design and Vercel that enables direct deployment of designs to the Vercel platform. The feature likely streamlines the workflow for dev
arXiv:2507.17853v3 Announce Type: replace Abstract: Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges whe
arXiv:2602.04291v2 Announce Type: replace Abstract: Multi-expert systems, where multiple Large Language Models (LLMs) collaborate to solve complex tasks, are increasingly adopted for high-performance
arXiv:2606.22982v1 Announce Type: new Abstract: Multi-arm manipulation demands precise spatiotemporal coordination, yet many centralized approaches scale poorly as team size increases. To address this
arXiv:2606.21322v1 Announce Type: new Abstract: Detecting when a nonlinear dynamical system departs from its normal regime is a recurring problem across the sciences, from cardiology to climate and en
arXiv:2606.20651v1 Announce Type: cross Abstract: Autonomous drone swarms in space-constrained environments such as warehouses, inspection corridors, and urban delivery routes must share limited airsp
arXiv:2606.22436v1 Announce Type: new Abstract: Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed stochastic noise. Exi
arXiv:2606.23453v1 Announce Type: new Abstract: Location encoders transform geographic coordinates into high dimensional embeddings for downstream machine learning, but it is unclear how well these re
arXiv:2509.17901v4 Announce Type: replace Abstract: Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail,
arXiv:2606.21249v1 Announce Type: new Abstract: Retrieval heads, attention heads that copy information from earlier context to the current position, have been proposed as the mechanistic substrate for
arXiv:2506.23053v3 Announce Type: replace Abstract: Urban sensor networks need forecasts that are accurate, carry useful uncertainty, and refresh fast enough to act on as new readings arrive. These go
arXiv:2606.22625v1 Announce Type: new Abstract: Degraded document image binarization is sensitive to domain shifts caused by paper aging, bleed-through, stains, shadows, and uneven illumination, and t
arXiv:2606.23031v1 Announce Type: new Abstract: Reconstructing dynamic urban scenes remains challenging due to the unbounded nature of driving environments and the presence of multiple dynamic objects
arXiv:2606.20663v1 Announce Type: cross Abstract: Large Language Models have the potential to expand and improve the access to clinical information by enabling new ways of interacting with medical kno