Knowledge catalogue
arXiv:2603.03072v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures
Today we're launching Base Labs, a research lab by Baseten. Our mandate is to make open-source as useful as possible, and our one rule is that we publish without exception, including what fails. Up un
arXiv:2609.02067v1 Announce Type: new Abstract: Scientific benchmarks are commonly built by domain experts who write tasks and cross-check one another's work, or who adapt existing material from textb
arXiv:2609.01765v1 Announce Type: new Abstract: Carbon markets put a price on emissions, yet that price remains hard to forecast. Work in this area clusters on the EU and Chinese schemes, compresses r
arXiv:2609.02830v1 Announce Type: new Abstract: LiDAR-based semantic segmentation is a core perception module for autonomous vehicles and mobile robots. Despite the strong performance of recent state-
arXiv:2510.06257v2 Announce Type: replace-cross Abstract: Quantum error correction (QEC) is essential for scalable quantum computing, yet decoding errors via conventional algorithms result in limited
arXiv:2609.02364v1 Announce Type: cross Abstract: Existing Human-Robot Interaction (HRI) literature has focused on identifying and structuring errors, failures, conflicts, and knowledge issues (called
arXiv:2609.02157v1 Announce Type: new Abstract: Physical reservoir computing (PRC) refers to the use of a physical dynamical system as a computational resource for tasks such as state estimation and c
arXiv:2609.02440v1 Announce Type: cross Abstract: Adversarially robust models often overfit to a specific attack budget, necessitating multiple specialized models for diverse and dynamic adversarial e
arXiv:2609.02861v1 Announce Type: cross Abstract: Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the s
arXiv:2609.02341v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) have shown strong potential in autonomous driving by leveraging multimodal pretraining for instruction following, v
arXiv:2609.02702v1 Announce Type: new Abstract: Transformers process information causally, but long-context reasoning may depend on task state discovered only later. We formalize this mismatch through
arXiv:2609.02006v1 Announce Type: cross Abstract: A compressed student has two shapes that need not agree: the weight it deploys at inference and the weight family its training can reach. We show that
Hey everyone, Wanted to share a short paper we just published exploring a simple but surprisingly effective optimization for sparse MoE reasoning models. The problem: MoE reasoning models (especially
arXiv:2609.02499v1 Announce Type: cross Abstract: Recommender-system experiments often rely on a single random training seed, assuming that run-to-run stochasticity has limited impact on evaluation co
arXiv:2609.02540v1 Announce Type: new Abstract: Diagnosing collective anomalies from urban trajectories is increasingly important for traffic governance, as it reveals what happened, who was involved,
arXiv:2609.02082v1 Announce Type: cross Abstract: Visual modality enhances the capabilities of multimodal large language models (MLLMs) but also introduces a safety concern: a benign textual query may
arXiv:2609.01699v1 Announce Type: new Abstract: The rapid growth of AI computing has driven increasing demands for flexible and high-capacity data-center interconnections. Owing to its ultra-wide band
arXiv:2609.01731v1 Announce Type: new Abstract: Multi-Unmanned Aerial Vehicle (UAV) disaster-response systems require coordinated task assignment and local trajectory control, yet the individual and c
arXiv:2609.01738v1 Announce Type: new Abstract: Unexploded ordnance (UXO) continues to restrict civilian access, agricultural activity, infrastructure recovery, and environmental remediation in contam
arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer E
arXiv:2609.02476v1 Announce Type: new Abstract: Wireless Capsule Endoscopy (WCE) captures and streams video while passing through a patient's Gastrointestinal (GI) tract and is used to examine its irr
arXiv:2609.02434v1 Announce Type: new Abstract: Restoring images degraded by adverse weather remains challenging due to spatially heterogeneous degradations. Many existing weather-specific restoration
arXiv:2609.02652v1 Announce Type: new Abstract: Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol. Its kernel decodes one shell; we found n
arXiv:2609.02134v1 Announce Type: new Abstract: Humanoid learning increasingly relies on transforming vast and diverse human motion data into high-quality robot reference trajectories. However, retarg
arXiv:2505.12912v2 Announce Type: replace Abstract: Pre-trained vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated a remarkable generalizability, enablin
arXiv:2609.02754v1 Announce Type: cross Abstract: Large language models now answer medical questions with expert-level performance. However, the context these systems act on can be misleading, and mis
arXiv:2609.02859v1 Announce Type: new Abstract: Harnessing naturally occurring feedback from user interactions offers a promising learning signal for Large Language Models (LLMs). However, recent stud
arXiv:2507.08468v2 Announce Type: replace Abstract: This paper provides an experimental evaluation of the capability of large language models (LLMs) to assist in legal decision-making within the frame
arXiv:2609.02421v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planni
arXiv:2609.01788v1 Announce Type: cross Abstract: Real-world communication often requires pragmatic reasoning: interpreting meanings implied through context and cultural convention rather than stated
Bloomberg: Vals analysis: open-weight models performing multi-stage tasks, like building a web app, can have an environmental impact 10K times greater than simple queries — Benchmarker Vals AI finds t
arXiv:2609.02776v1 Announce Type: new Abstract: Palm-vein biometrics are increasingly used for secure, contactless authentication. Yet real-world deployment exposes them to surface noise (sweat, dirt)
arXiv:2509.26604v2 Announce Type: replace Abstract: Existing multimodal audio generation models often lack precise user control, which limits their applicability in professional Foley workflows. In pa
arXiv:2609.01816v1 Announce Type: new Abstract: We introduce Video2Reaction, a multimodal dataset that maps short movie segments to the induced emotional reactions of viewers in the wild, as expressed
arXiv:2602.23771v2 Announce Type: replace-cross Abstract: Remote photoplethysmography (rPPG) enables contact free monitoring of vital signs and is especially valuable for neonates, since conventional
arXiv:2609.02462v1 Announce Type: new Abstract: End-to-end autonomous driving in urban environments requires robust decision-making under partial observability and complex multi-agent interactions. Se
arXiv:2609.02486v1 Announce Type: cross Abstract: Document Visual Question Answering (DocVQA) often leverages Retrieval-Augmented Generation (RAG), where late-interaction encoders are commonly used to
arXiv:2601.07795v2 Announce Type: replace Abstract: The European Space Agency (ESA), driven by its ambitions on planned lunar missions with the Argonaut lander, has a profound interest in reliable cra
arXiv:2609.02291v1 Announce Type: cross Abstract: Ultra-low bitrate video compression still faces critical challenges: traditional neural video compression inevitably introduces blurring artifacts, wh
arXiv:2512.05211v2 Announce Type: replace Abstract: Morphing aerial robots have the potential to transform autonomous flight, enabling navigation through cluttered environments, perching, and seamless
arXiv:2606.16600v2 Announce Type: replace Abstract: Expressive co-speech gestures are crucial for natural human--robot interaction, yet generating them on physical humanoid robots remains challenging
We have been working on an open-source, model-neutral agent harness for general purpose agents called TrueForge, and wanted to understand how much the harness itself actually matters. So we ran 14 tas
We have secured nearly TWO MILLION DOLLARS IN TOKENS from leading labs. Lead by @AIatMeta as Founding Token Patron and joined by @AnthropicAI, @OpenAI, and @FireworksAI_HQ this is an incredible haul o
On September 3, 2026 Sam Altman announced that the release of OpenAI’s blog post on **“GPT‑6 Astra: A new generation of intelligence”** experienced a brief deployment snag, yet he noted the content is
Continual learning isn't some fake term but a real goal and arguably one of the most important open ones in 2026. It roughly means: ‘building systems that keep acquiring useful knowledge or skills aft
WeatherNext 3 will begin enhancing weather experiences within Google Search, @GeminiApp, @googlemaps, @GMapsPlatform Weather API and @googleearth Engine starting today Dive into the tech: https://blog
arXiv:2609.02177v1 Announce Type: cross Abstract: Multi-bit watermarking for large language models (LLMs) enables content source tracing by embedding user-identifiable messages into generated text. Ex
We've benchmarked all the latest frontier models on hard document extraction tasks (with Fable 5.1 and Gemini 3.8 Flash coming soon!). ExtractBench is now live on @kaggle . 5.6 Sol leads the pack, fol
What a super interesting paper this one is. They propose an architecture for agents that outlive their model, harness and host. Today we describe an agent by whatever model and harness it happens to r
The job of doing inference is not the same for every model ou there, as it depends on the architecture and configurations and the available machines. Many times we would not have the right machines to
What exactly does it it mean for monitorability that 'The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4' @merettm? (And did you me
arXiv:2609.02322v1 Announce Type: cross Abstract: The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at al
arXiv:2607.17952v2 Announce Type: replace Abstract: Climate disclosure classification is a fundamental task for analysing corporate climate disclosures, yet such disclosures appear in many different s
arXiv:2609.01985v1 Announce Type: new Abstract: As LLM coding agents increasingly perform end-to-end engineering work, we lack empirical characterization of how they behave on systems-level requiremen
arXiv:2609.01741v1 Announce Type: new Abstract: Statutes are increasingly parsed by machines before people read them, and the parsers disagree: on Missouri's statutes, two independently written extrac
arXiv:2505.15276v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have achieved remarkable success on complex tasks, yet their tendency to 'overthink' leads to inefficiencies. Although
arXiv:2609.02438v1 Announce Type: new Abstract: Large language models can look capable of logical reasoning, but correct or incorrect answers alone tell us little about what the model represents inter
arXiv:2609.01814v1 Announce Type: new Abstract: Information sharing can improve a pooled estimate while eliminating independent rescue actions. This paper separates those effects in exact finite disco
arXiv:2608.27984v2 Announce Type: replace Abstract: Multi-Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration topologies. However, existing topolog