Knowledge catalogue
arXiv:2608.23582v1 Announce Type: cross Abstract: We present the Transformer Accelerator (TFA), a synthesizable, parameterizable INT8 memory-to-memory engine for transformer inference. One time-multip
arXiv:2608.24119v1 Announce Type: cross Abstract: Visual demonstrations provide a natural interface for specifying image transformations that are difficult to describe exhaustively with text. However,
trust us? LMAO. TIME’s new cover: In 2026, OpenAI has seen key departures, rogue AI agents, major lawsuits, and has seen increased competition in the AI race. “We clearly had some missteps as a compan
arXiv:2608.24019v1 Announce Type: cross Abstract: Underactuated systems pose a challenge for convex motion planning because their dynamically feasible motions lie on a manifold of trajectories in func
arXiv:2608.23763v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness int
— Try it out in the @Geminiapp on macOS and Gboard on @Android — Build in the Gemini API via @googleaistudio, @antigravity, and the Gemini Enterprise Agent Platform (public preview) — Coming soon to @
arXiv:2608.24674v1 Announce Type: new Abstract: Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal
arXiv:2606.18699v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown impressive capabilities across diverse tasks, yet their performance on jurisdiction-specific legal rea
arXiv:2411.12965v3 Announce Type: replace-cross Abstract: Nearest neighbor (NN) algorithms have been extensively used for missing data problems in recommender systems and sequential decision-making sy
arXiv:2511.08873v3 Announce Type: replace Abstract: Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning me
arXiv:2608.23857v1 Announce Type: new Abstract: Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks. Their two primary observations, land surface tempe
Benchmarked qwen3.8 xhigh, medium and muse glimmer. Xhigh effort mode with qwen3.8 took almost 30hrs. (And still failed on 16 cases because of the 32K output token limit) Medium effort mode and muse g
arXiv:2510.02570v2 Announce Type: replace Abstract: Human review of consequential decisions by face recognition algorithms creates a collaborative human-machine system. We establish the circumstances
arXiv:2508.21424v3 Announce Type: replace Abstract: Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that
We continue to iterate on the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format. But a big question remains: How can you sha
What's Changed MLX: Qwen3.8 Flash Next support cmake: make external compat patches idempotent MLX and llama.cpp update mlxrunner: add structured output support mlxrunner: avoid Metal GPU timeouts when
arXiv:2608.24241v1 Announce Type: cross Abstract: Reproducibility of heart rate variability (HRV) analysis is limited by differences in preprocessing and computational conventions across software plat
arXiv:2608.24366v1 Announce Type: new Abstract: End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degra
arXiv:2608.23728v1 Announce Type: new Abstract: Satellite orbit prediction, which aims to forecast future orbital trajectories from historical observations, is important for collision warning and safe
arXiv:2509.18778v2 Announce Type: replace-cross Abstract: Visual imitation learning frameworks allow robots to learn manipulation skills from expert demonstrations. While existing approaches mainly fo
arXiv:2608.24302v1 Announce Type: new Abstract: Long-video understanding depends critically on how a limited model context is constructed from a much longer video. Existing approaches improve this pro
arXiv:2608.24618v1 Announce Type: new Abstract: Over the past decade, autonomous robotic systems have been increasingly deployed in applications such as surveying, search and rescue, and last-mile del
arXiv:2608.24063v1 Announce Type: cross Abstract: While Vision Large Language Models (VLLMs) have achieved remarkable success in multimodal reasoning, their long-context inference remains prohibitivel
arXiv:2608.24169v1 Announce Type: new Abstract: 3D geometry editing is a critical yet labor-intensive part of the graphics pipeline, requiring artists to translate creative intent into precise operati
arXiv:2608.24430v1 Announce Type: new Abstract: Responsible deployment of face verification systems requires more than accurate decisions: systems should also provide interpretable and auditable evide
arXiv:2608.24535v1 Announce Type: new Abstract: Data visualizations are widely used for communicating information, but they are also vulnerable to intentional manipulations that induce misleading inte
arXiv:2510.12524v2 Announce Type: replace Abstract: Unsigned Distance Fields (UDFs) provide a flexible representation for 3D shapes with arbitrary topology, including open and closed surfaces, orienta
arXiv:2512.12895v2 Announce Type: replace Abstract: Reasoning models (e.g., DeepSeek-R1) generate long chains of thought to solve harder problems, but they often loop, repeating the same text at low t
Want to test how good GLM-5.3-Flash is? I have been finding it useful for visual explainers using /eli5. Try it with Pi or Hermes Agent in our new agent playground: https://academy.dair.ai/dashboard/p
arXiv:2608.24479v1 Announce Type: new Abstract: Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for d
We benchmarked 20+ open-weight models on easy-to-hard document extraction tasks through ExtractBench. The results are all available on @huggingface 🤗 ExtractBench is a schema-guided extraction benchma
We built one of the most comprehensive benchmarks for document extraction, and evaluated it across a lot of different systems: ✅ one-shot frontier VLMs ✅ frontier VLMs + coding agent harnesses ✅ one-s
We have conducted a thorough investigation into the Hugging Face incident. We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing sa
we made vision mlx quants of qwen3.8 27b (9 builds from 8bit at 29.5 GB down to 3.23bpw DWQ at 11.8 GB) and compared them against other community vision mlx quants from hf (we only compared vision bui
We worked with METR and Redwood Research to conduct a third-party assessment of the model behavior observed during the incident. They’re sharing a report of their findings: https://metr.org/blog/2026-
arXiv:2607.18467v2 Announce Type: replace Abstract: Many operational decisions rely on predictive models that estimate uncertain outcomes conditional on observable contexts. Training such models, howe
arXiv:2608.24756v1 Announce Type: new Abstract: Seagrass meadows are crucial blue-carbon habitats, and mapping their extent is a prerequisite for coastal management and carbon inventory. Optical satel
arXiv:2608.24017v1 Announce Type: cross Abstract: The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent
arXiv:2608.24053v1 Announce Type: new Abstract: Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space f
We’re excited to announce that 𝗛𝗮𝗿𝗿𝗶𝘀𝗼𝗻 𝗖𝗵𝗮𝘀𝗲 @hwchase17, Co-Founder & CEO of @LangChain, will be speaking at VapiCon 2026! 🎙️ Harrison co-founded LangChain with the goal of making it easier to use LL
arXiv:2608.24142v1 Announce Type: new Abstract: Prompt learning adapts vision-language models such as CLIP by optimizing continuous prompt vectors, but the learned prompts are difficult to interpret i
arXiv:2608.24881v1 Announce Type: cross Abstract: Generative models are commonly ranked by Frechet Inception Distance (FID) and Kernel Inception Distance (KID), yet FID's first-two-moment summary can
arXiv:2608.24022v1 Announce Type: cross Abstract: LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable t
What happens when there are more agents than eyeballs browsing the internet? How will the economics of the internet be reinvented? @paraga thinks Shapley values may hold the answer. Parag built Twitte
arXiv:2608.23766v1 Announce Type: cross Abstract: Between AI-assisted item generation and expert review sits a computational evaluator whose decisions are usually treated as technical preliminaries. Y
What's better than an open-weight multimodal model release? Well, the technical report. I just love how these labs like Qwen and DeepSeek continue to drop gem after gem. Qwen3.8-Flash is the latest in
arXiv:2606.13705v2 Announce Type: replace-cross Abstract: The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as TV episodes, the 88 IAU conste
arXiv:2608.24492v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where grou
arXiv:2608.24381v1 Announce Type: new Abstract: Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missing
arXiv:2608.24080v1 Announce Type: cross Abstract: In psychological counseling, effective support is not always delivered through long, information-rich responses. Minimal responses, such as backchanne
arXiv:2608.23623v1 Announce Type: cross Abstract: Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, bu
arXiv:2608.24569v1 Announce Type: new Abstract: Large language model (LLM) agents coordinate complex tasks through multi-role and multi-stage workflows. Upstream state is repeatedly transformed into i
arXiv:2608.23978v1 Announce Type: new Abstract: Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a cen
arXiv:2608.24631v1 Announce Type: cross Abstract: Similarity in many decision systems is governed not by distance alone but by interactions among variables. In fraud and anomaly detection, small local
arXiv:2608.23780v1 Announce Type: cross Abstract: LLMs are being used increasingly to measure aspects of student discourse (e.g. talk moves, collaboration, equity of voice) at scale. Typically, LLM-ba
arXiv:2608.24488v1 Announce Type: new Abstract: Many continuous-control policies are optimized as unbounded Gaussians and then mapped into bounded actions. We show that where entropy is measured chang
With only 6B active parameters, Qwen3.8-Flash-Next-Base tops 8 of 14 benchmarks, including MMLU-Pro, SuperGPQA, BBH and GSM8K. And it remains competitive with Qwen3.7-Plus-Base on the rest. Its 51B N-
arXiv:2608.23920v1 Announce Type: cross Abstract: We measure tablet-2, a production long-term memory engine for language models, on the text benchmarks the field already uses and on cross-lingual retr
arXiv:2608.24563v1 Announce Type: new Abstract: Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition properties such as types of camera lenses, se
arXiv:2608.24044v1 Announce Type: new Abstract: Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and pred