Knowledge catalogue
arXiv:2604.08366v1 Announce Type: cross Abstract: Large-scale deep learning models for physical AI applications depend on diverse training data collection efforts. These models and correspondingly, th
arXiv:2604.07126v1 Announce Type: cross Abstract: Predicting vehicle trajectories plays an important role in autonomous driving and ITS applications. Although multiple deep learning algorithms are dev
arXiv:2604.06332v1 Announce Type: cross Abstract: Autonomous highway driving, especially for long-haul heavy trucks, requires detecting objects at long ranges beyond 500 meters to satisfy braking dist
arXiv:2604.08362v1 Announce Type: new Abstract: The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user simulator. However, existing benchmarks remain co
arXiv:2604.07223v1 Announce Type: cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to int
arXiv:2604.06387v1 Announce Type: cross Abstract: Accurate reconstruction of environmental scalar fields from sparse onboard observations is essential for autonomous vehicles engaged in aquatic monito
Commands like `vc project ls` and `vc domains ls` now automatically use the scope of the linked local directory instead of defaulting to the global team. Previously, running these commands inside a...
Cognition is live in Japan! 🇯🇵 We launched today with Tokyo Merge - a standing room only event with industry leaders across the country. We’re hiring, partnering, and building in Japan. If you’re buil
maybe some nuance 😄 I don’t think anyone is “lying” about how great Mythos will be —> but there’s expectation misalignment between the Test Harness set up for Mythos and a belief it was given this cra
Sigma Automate Inc., a startup providing enterprises with no-code information technology automation, formally launched today with $2.75 million in funding to scale up its platform and expand its abili
Tesla puts a lot of effort into ensuring that our cars don’t run over animals More than 350 million vertebrate animals are killed by human driven vehicles every year. In general, autonomous vehicles a
Tejas Kumar ( a keynote speaker and developer with 20+ years of engineering experience across AI and web technologies ) presented on AI Harnesses at the AI Engineer Europe conference (April 8–10, 2...
This X (Twitter) Space, hosted by @TheBestOfAdam and featuring Replit's Samuel Spitz, was a live Q&A session aimed at helping people who are building with AI but encountering obstacles or roadblock...
Japanese railways don’t just run trains. They actually build cities and act as urban developers to capture the demand from transit. ~50% of revenue comes from owning the land around stations. Buy land
Part 5 of Replit's 6-part PM series, 'Vibe Coding Decks and Dashboards,' covers how product managers can use Replit's agentic workflows to produce slide decks, dashboards, and launch assets without...
SWE-1.6 is lightning fast! Here's what 950 tok/s feels like - available in Windsurf today. Media We’re releasing SWE-1.6, our best model in both intelligence & model UX. SWE-1.6 matches our Preview mo
GLM-5.1 is Z.ai's (zai-org) next-generation open-source flagship model for agentic engineering, achieving state-of-the-art performance on SWE-Bench Pro and significantly outperforming its predecess...
SWE-1.6 is free for everyone in Windsurf for the next 3 months at 200 tok/s. For paying users, we've partnered with Cerebras to serve the model at 950 tok/s. More technical details about this training
We’re releasing SWE-1.6, our best model in both intelligence & model UX. SWE-1.6 matches our Preview model on SWE-Bench Pro while dramatically improving on various behavioral axes. It’s available toda
With SWE-1.6 we've made significant progress on 'intelligence per token'. We post-trained the model from scratch (same pre-trained model) with a similar recipe as SWE-1.6 Preview. Our latest algorithm
Zapier reports 97% daily-work AI use and says its AI support-ticket summarizer halved average handle time.
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our
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
🔍 Search & Fetch APIs are now open to everyone! Powered by our in-house search engine, serving hundreds of millions of requests daily worldwide. 💰 Each endpoint: $0.75 per 1,000 calls. 📖 Docs: https:/
arXiv:2610.21882v1 Announce Type: cross Abstract: Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this kno
arXiv:2610.21984v1 Announce Type: cross Abstract: Autonomous driving planning requires selecting trajectories that remain safe, rule-compliant, and comfortable under complex multi-agent interactions,
arXiv:2610.09895v1 Announce Type: cross Abstract: We study a behavioral mechanism for artificial partiality in conversational agents. The paper reports no human-subjects data and makes no claim about
arXiv:2610.22323v1 Announce Type: new Abstract: Long-horizon robotic manipulation fundamentally requires memory: agents must retain task-relevant information from past observations and interactions an
arXiv:2610.22276v1 Announce Type: new Abstract: Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial re
arXiv:2610.21108v1 Announce Type: new Abstract: LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a
arXiv:2610.21514v1 Announce Type: cross Abstract: When code-repair agents fail, final tests reveal that a patch is wrong but not which earlier commitment caused it or which software obligation failed.
arXiv:2610.22056v1 Announce Type: new Abstract: Traditional reinforcement learning (RL) algorithms face significant limitations in handling long-term tasks with sparse rewards. Recent advancements hav
arXiv:2610.22150v1 Announce Type: new Abstract: In Rhetorical Structure Theory (RST), each edge of a discourse tree carries a nuclearity label, marking which span holds the central content, and a rela
arXiv:2610.20866v1 Announce Type: cross Abstract: Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints,
arXiv:2610.21156v1 Announce Type: new Abstract: Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing p
arXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to fre
arXiv:2610.21450v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chu
Google Antigravity is an agentic science workbench that consolidates multiple biological databases into a single interface, enabling biologists to rapidly discover, evaluate, and prioritize therapeuti
arXiv:2610.17310v1 Announce Type: new Abstract: Language-model agents are expected to adapt to others whose behavior changes through interaction. Yet adaptation may rely on learned behavioral patterns
arXiv:2610.17338v1 Announce Type: new Abstract: Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation
arXiv:2610.19811v1 Announce Type: cross Abstract: LLM workflows and agents rely on a set of binary decisions like allow/block an input, or discard/retain a retrieved document. When human deferral is u
arXiv:2610.18119v1 Announce Type: cross Abstract: {em Specification-Guided Reinforcement Learning (RL)} has largely concerned itself with learning an optimal policy against a formal specification in a
arXiv:2610.20085v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understand
arXiv:2610.19100v1 Announce Type: cross Abstract: Constructing robust GUI agents relies on multimodal visual grounding: the ability to precisely map natural language intents to actionable on-screen co
arXiv:2610.16108v1 Announce Type: new Abstract: Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consen
Harnesses + smart models = the end of the last famous hard benchmarks. Models can now work for extremely long times (bye, METR Long Tasks), they can output professional documents with correct math (so
arXiv:2610.19179v1 Announce Type: cross Abstract: We study packet routing in queuing systems where queues act as selfish, myopic agents that use no-regret learning algorithms to select servers with un
Meta AI Research: Meta releases Muse Spark Open, saying it is the most capable US open-weight model, with 816B total and 42B active parameters and a 1M-token context window — Muse Spark Open is availa
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-GGUF NVIDIA Nemotron 3.5 Bolt 74B-A9B 24GB is a vi
Alix Coutures / The Information: OpenAI continues to work to grow its ad business in ChatGPT, cutting ad rates, chasing small and midsize businesses, and hiring some new talent from Meta — As OpenAI h
arXiv:2610.20009v1 Announce Type: new Abstract: Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching perf
New York Times: Q&A with Dwarkesh Patel on his podcast, lessons from history, AGI, the mood in San Francisco, the Hugging Face hack, Chinese AI, pacing the frontier, and more — Dwarkesh Patel on what
arXiv:2610.04561v2 Announce Type: replace Abstract: Differentiable programming connects scientific computation with gradient-based inference, learning and design. Extending these capabilities across a
arXiv:2610.19795v1 Announce Type: new Abstract: Video world models aim to simulate complex environments with realistic appearance and dynamics. Maintaining consistency over long interactions requires
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitat
NVIDIA Nemotron 3.5 Super NVIDIA Nemotron 3.5 Super is a vision-language model for coding, reasoning, tool use, and document understanding. It pairs a 120B-parameter hybrid Mamba-2/Transformer mixture
Overview llama.cpp v0.7.0 adds the LiliCorr speculative decoding technique and MTP for GLM5-Next, a new GPU cache for MoE experts kept in host memory (--moe-cache-mib, up to ~2.2x decode speedup when
arXiv:2610.18158v1 Announce Type: new Abstract: Learning dealer agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but
arXiv:2610.15966v1 Announce Type: new Abstract: We present a low-cost miniature Ackermann vehicle for embedded neural-driving research, organized as a hardware-partitioned perceive-decide-act agent: a
arXiv:2610.17970v1 Announce Type: cross Abstract: Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while