Knowledge catalogue
arXiv:2604.07705v1 Announce Type: new Abstract: Aerial vision-and-language navigation (Aerial VLN) aims to enable unmanned aerial vehicles (UAVs) to interpret natural language instructions and autonom
arXiv:2604.08509v1 Announce Type: new Abstract: Digital human generation has been studied for decades and supports a wide range of real-world applications. However, most existing systems are passively
arXiv:2604.06464v1 Announce Type: new Abstract: Conformal prediction provides distribution-free prediction intervals with finite-sample coverage guarantees, and recent work by Snell & Griffiths refra
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not
arXiv:2604.06901v1 Announce Type: cross Abstract: Conventional career guidance platforms rely on static, text-driven interfaces that struggle to engage users or deliver personalised, evidence-based in
The *Interconnects.ai* article argues that fears around releasing an open-weight version of Claude Mythos are overstated, noting that closed frontier models still lead open-weight ones in robust, ...
ConvApparel is a human-AI conversation dataset and comprehensive evaluation framework designed to quantify the 'realism gap' in LLM-based user simulators and improve the training of robust conversa...
Having a model like Gemma 4, which is perfectly adequate for everyday use in many cases, runs locally, is free, and secure, still feels unreal. We have a very good AI that costs nothing, uses hardly a
Nous Research's Hermes model line has been deliberately developed with a strong emphasis on creative capability. The training dataset for Hermes 4 expanded to 50x more data tokens than Hermes 3, w...
Science needs a way to process models that are only 'mostly correct' in terms of their predictions, but are very compressive (high ratio between predictive power and model complexity). They are likely
Simplicity is a very strong signal of model quality. Galileo's heliocentric model was directionally correct, but its predictive power was quite bad compared to the much older Ptolemaic model, because
We should view the history of physics as a long-running program synthesis task. Kepler and Newton were searching the space of possible symbolic models to find the simplest one that would best satisfy
Muse Spark is the first model from Meta's Superintelligence Labs division and the debut entry in the new Muse model family, representing a 'ground-up overhaul' of the company's AI efforts. It is ...
This post walks you through understanding audio embeddings, implementing Amazon Nova Multimodal Embeddings, and building a practical search system for your audio content. You'll learn how embeddings r
Common Failure Modes Break VLM-Powered OCR in Production. 🔁 Repetition Loops — model spirals into infinite whitespace, exhausts resources, cascades latency across your system 🛑 Recitation Errors — saf
Building and serving models on infrastructure is a strong use case for businesses. In Google Cloud, you have the ability to design your AI infrastructure to suit your workloads. Recently, I experiment
The specific tweet (status ID 2041723225827062080) could not be directly retrieved, but based on closely related content from Ethan Mollick's (@emollick) X account, the most relevant match is the p...
ui : Discover & Download Models from HF Hub (#29584) common : resolve - download tags and list cached sidecars A Q4_0-mtp style tag now resolves the sidecar file when no model file matches it, so a so
Great application of small language models from Salesforce and colleagues. AI-scientist pipelines are well known to struggle to propose novel and diverse research ideas. This team trains an 8B reasoni
Total Parameters 4B Architecture Looped (latent-recurrent) normalized-GPT with interleaved sliding-window attention (SWA) and full-attention layers Precision BF16 Context Length Up to 256K tokens Supp
Defiance puts DavidAU's Turbo-Brilliance 'AI Construct' modes on HauhauCS's uncensored Qwen3.8-27B. You pick a mode (Joker, Dr. House, a 20-agent Einstein panel, a Socratic tutor) per request, and the
I use Pi/OpenCode for coding tasks which still seems to be the most popular, but I'm wondering what you guys use for normal chat interface. It's been a few months since I've seen discussions about har
I know everyone's excited about 3.8, but honestly I'm still refining 3.6. And I hate the way 3.8 talks, so... I keep seeing all these posts about what's the use of open source, so I figured I'd submit
arXiv:2610.22341v1 Announce Type: cross Abstract: We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises
arXiv:2610.21243v1 Announce Type: cross Abstract: Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective perform
arXiv:2512.03687v2 Announce Type: replace Abstract: Active visual perception enables an intelligent system to improve perception by controlling how visual evidence is acquired. However, differences in
arXiv:2506.03371v2 Announce Type: replace Abstract: Recent advances in vision-language models (VLMs) have enabled accurate image-based geolocation, raising serious concerns about location privacy risk
arXiv:2610.21147v1 Announce Type: new Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and leng
arXiv:2610.20785v1 Announce Type: new Abstract: Large language models are increasingly used in social interactions, where appropriate responses require recognizing implicit cues, inferring mental stat
arXiv:2610.21055v1 Announce Type: new Abstract: Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence. We study a weaker form that can
arXiv:2610.21586v1 Announce Type: cross Abstract: Indoor service robots often enter unmapped buildings whose layouts and task constraints are already familiar to users. We address this human-familiar,
Alibaba's Qwen team released a new repository on Wednesday, October 14, 2026. Its goal is to measure how well visual agents can create 3D scenes in Blender based on real-world references. https://gith
arXiv:2610.21525v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive capabilities across many tasks, including processing large amounts of text, following instructions, a
arXiv:2610.21508v1 Announce Type: new Abstract: Large language models (LLMs) predict neural responses during naturalistic language comprehension, but the linguistic information underlying this brain a
arXiv:2610.22062v1 Announce Type: cross Abstract: Objective: Trofinetide, approved in 2023 as the first Rett syndrome treatment, lacks scalable real-world monitoring because chart review is labor-inte
arXiv:2610.22333v1 Announce Type: new Abstract: Large language models (LLMs) can often tell when they are being tested. This ability, known as evaluation awareness, can lead models to act more cautiou
arXiv:2610.21348v1 Announce Type: new Abstract: Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deploym
arXiv:2610.21257v1 Announce Type: cross Abstract: Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations in linear projections dominate compute and ene
arXiv:2610.21149v1 Announce Type: new Abstract: Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts. However, exis
arXiv:2610.21767v1 Announce Type: new Abstract: Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a
arXiv:2610.21452v1 Announce Type: cross Abstract: Human face-to-face conversation requires coordinating speech, gestures and expressions across both speaking and listening. We present ELLSA 2, an end-
arXiv:2610.21537v1 Announce Type: new Abstract: Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual learning
arXiv:2610.20814v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards often trains language models on responses generated by a different, possibly stale behavior policy. Cor
arXiv:2610.21167v1 Announce Type: new Abstract: Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet multi-hop, long-horizon tasks remain challenging.
arXiv:2610.22360v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) and 3D generation have expanded 3D understanding and synthesis. However, beyond visual fidel
arXiv:2610.21708v1 Announce Type: cross Abstract: When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a meas
arXiv:2509.16998v2 Announce Type: replace Abstract: Design for Robotic Assembly (DfRA) remains largely dependent on manual planning and heuristic simulation, limiting scalability and robustness in com
I've been maintaining my own chat template for Qwen3.8-Flash-Next, and after a discussion in another thread I decided to share it. I made a repo with my v1.4 template, the original Unsloth fixed stock
K3 came out in July hyped as the best open model you could download, and it scored 57 on Artificial Analysis, right up there with Opus 4.8 and GPT-5.5. I went back to see what running it actually look
arXiv:2412.07251v1 Announce Type: cross Abstract: Large language models have exhibited significant enhancements in performance across various tasks. However, the complexity of their evaluation increas
arXiv:2610.22244v1 Announce Type: cross Abstract: Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users writ
arXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and error
arXiv:2601.21132v2 Announce Type: replace Abstract: I demonstrate that large language models can infer ethnicity from names with accuracy exceeding that of Bayesian Improved Surname Geocoding (BISG) w
arXiv:2610.20951v1 Announce Type: new Abstract: Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text. Like t
arXiv:2610.21794v1 Announce Type: new Abstract: Despite the remarkable generalization capabilities of Large Language Models, generating clinically accurate and structured radiology reports from medica
arXiv:2610.22240v1 Announce Type: new Abstract: Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence. However, training such agents rema
arXiv:2610.22043v1 Announce Type: cross Abstract: Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, no
arXiv:2610.20965v1 Announce Type: new Abstract: Large multimodal models have achieved remarkable progress by scaling model capacity and training on massive paired multimodal data. However, this paradi
Muse Spark Open is now live on Wally, day 0 Best US open model thanks to @finkd 370 tok/s, ~2x faster than any provider on OpenRouter. $5 Free on signup. Media 1/ muse spark open is the most capable U
arXiv:2609.08183v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into