Knowledge catalogue
Mistral AI announced its Le Chonk model, which performs visual grounding by accurately locating objects within images. On the Dense 200 benchmark it achieved a 42 % score, outperforming even frontier‑
🇫🇷 Le Chonk joins the sudo L7 leaderboard 🇫🇷 We just added @MistralAI's Mistral Large 4 to sudo L7, our benchmark for staff-level software engineering. Mistral Large 4 scores 13.3%, ahead of Muse Spar
Chao Kong / South China Morning Post: Leading Chinese mathematicians launch an alliance, including eight orgs and aiming for 1,000+ scientists, to focus on developing specialized AI models for math —
arXiv:2610.12886v1 Announce Type: new Abstract: Action-chunking policies predict future controls but execute only a prefix before replanning. How should a fixed action-token budget be organized to sup
arXiv:2610.13442v1 Announce Type: cross Abstract: Compression schemes provide a general framework for deriving data-dependent risk bounds for learning algorithms. For learning rules based on preferent
arXiv:2610.12933v1 Announce Type: new Abstract: Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can subs
arXiv:2610.13234v1 Announce Type: new Abstract: Lagrangian Neural Networks (LNNs) learn dynamics from trajectory data by parameterizing a scalar Lagrangian and deriving accelerations through the Euler
arXiv:2610.13640v1 Announce Type: new Abstract: In this paper we describe a Constraint Acquisition Tool that generates size independent constraint programs from input data and positive and negative ex
arXiv:2601.07665v2 Announce Type: replace-cross Abstract: We introduce a principled learning to optimize (L2O) framework for solving fixed-point problems involving general nonexpansive mappings. Our i
arXiv:2610.09002v2 Announce Type: replace Abstract: When a team of agents shares a reward for completed tasks, reporting and stopping unsafe work reduces the team's reward. Random audits that penalize
least clickbait slop post China has killed the entire vector database industry. They open-sourced TencentDB Agent Memory. It gives any AI agent long-term memory that runs 100% locally. No Pinecone. No
https://preview.redd.it/3ekngxk224vh1.png?width=1080&format=png&auto=webp&s=9bfe5c92033e17d5b2fb4529f1320c99455a138b I built a GPU compiler and wrote an article about it, focusing on concepts shared b
arXiv:2610.13148v1 Announce Type: cross Abstract: In this work, we revisit the classic Les Miserables benchmark network from the perspective of social communication. Using the 1998 film adaptation of
arXiv:2606.15457v2 Announce Type: replace-cross Abstract: 3D FLAIR MRI is widely recommended as one of the standard MRI sequences for brain imaging in multiple sclerosis (MS), but publicly available M
arXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Me
arXiv:2610.12818v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically tra
arXiv:2610.13040v1 Announce Type: cross Abstract: Consumer rotating devices, including washing machines, air conditioners, electric fans, robotic vacuum cleaners, and home fitness equipment, increasin
arXiv:2302.07373v2 Announce Type: replace Abstract: We introduce LOT Wassmap, a computationally feasible algorithm to uncover low-dimensional structures in the Wasserstein space. The algorithm is moti
I've made a few posts recently, just talking about the hardware I've got and the model I use. Pair of P100s, Unsloth Qwen3.6 35b A3B UD Q4 K XL. There's been a ton of talk of model and hardware specif
Quick context: LocalLightChat (LLC) is a chat frontend for local LLMs. Download it, run it, that's it. No installation (unless you want to), no dependencies, and it runs on pretty much anything, inclu
arXiv:2506.09956v2 Announce Type: replace-cross Abstract: Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the pra
arXiv:2610.13437v1 Announce Type: new Abstract: Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic str
arXiv:2610.12870v1 Announce Type: cross Abstract: Practical ship design requires localized refinement and performance evaluation. This paper presents a reward-directed diffusion framework for localize
arXiv:2602.13619v2 Announce Type: replace-cross Abstract: We study parametric change-point detection under local differential privacy, focusing on the offline localization of a single change point in
arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-
arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Exi
arXiv:2610.13131v1 Announce Type: new Abstract: Trajectory generation underpins urban applications such as traffic management and urban planning. Within road networks, vehicle movement along road segm
arXiv:2610.12518v1 Announce Type: cross Abstract: This position paper argues that the generative molecular dynamics (GenMD) community is not properly evaluating its progress: current evaluations let a
arXiv:2610.13158v1 Announce Type: new Abstract: Reactive collision avoidance in unknown, cluttered environments must perceive obstacles and correct motion within milliseconds. Existing methods rely on
arXiv:2610.13028v1 Announce Type: new Abstract: Neural operators that learn physical laws from data should generalize beyond their training distribution and expose the learned law in closed form. The
arXiv:2610.13590v1 Announce Type: cross Abstract: Recent results [arXiv:2602.04378, arXiv:2602.22608] have established worst-case objective-error lower bounds of order 1/T^2 after T linear minimizatio
I built a spotlight search for windows. It has an embedding model and a MoE models to go with it. The MoE It's 2 Qwen 3.5 4B models, I fine tuned one for coding work and another for agentic work, and
arXiv:2610.12638v1 Announce Type: cross Abstract: Day-ahead electricity forecasts can help building operators schedule heating, ventilation, and other services around anticipated demand. Choosing a fo
arXiv:2610.13717v1 Announce Type: new Abstract: Federated clustering can support applications such as patient stratification across hospitals and customer segmentation across distributed financial dat
arXiv:2610.12757v1 Announce Type: new Abstract: Task-oriented conversational agents remain fragile under realistic conditions, especially when users exhibit non-cooperative behavior. Existing function
arXiv:2610.12659v1 Announce Type: new Abstract: Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether
arXiv:2610.13534v1 Announce Type: new Abstract: Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. E
arXiv:2610.13409v1 Announce Type: new Abstract: End-to-end planning in complex scenes must model diverse driving intentions and select the most appropriate trajectory using scene context and future ri
arXiv:2610.13838v1 Announce Type: new Abstract: Nearly every autonomous or semi-autonomous flipper controller assumes access to an elevation map of the terrain under and in front of the robot. The ter
arXiv:2610.13772v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulato
arXiv:2610.12537v1 Announce Type: new Abstract: When a trader executes a large order, the relevant question is not what will the price be? but what would the price have been had I not traded? Market i
arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demon
arXiv:2610.13755v1 Announce Type: cross Abstract: Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group o
arXiv:2610.12954v1 Announce Type: new Abstract: This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted r
arXiv:2610.13829v1 Announce Type: cross Abstract: A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one
arXiv:2610.13583v1 Announce Type: new Abstract: Detectors of machine-generated text score almost perfectly on scientific-literature benchmarks, implying we can reliably distinguish with these detector
arXiv:2610.13594v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) is a key driver for Large Reasoning Models, but it is vulnerable to 'zero-reward collapse', a trai
arXiv:2610.12618v1 Announce Type: cross Abstract: Physics foundation models are an increasingly popular approach for building versatile emulators for spatiotemporal systems. They require tokenisation
Meta is making up for lost time in the AI race. After launching Muse Spark, the first model from its revamped Superintelligence Labs division, and buzzy AI agent Muse, it's now launching two new model
Meta AI Research: Meta introduces Muse Wonder and Muse Wonder Full, saying they deliver state-of-the-art performance on personal and professional agentic tasks — Fourteen months ago, we began a ground
arXiv:2610.12794v1 Announce Type: cross Abstract: Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization
Meta Platforms Inc. today released Muse Wonder and Muse Wonder Full, two artificial intelligence models it says are its most capable yet at running agents that handle personal and professional tasks.
Robert Hart / The Verge: Meta says it plans to power its Muse AI agent with Wonder, starting with subscribers, and will develop specialized models it “can bring to everyone using Muse” — Meta says the
arXiv:2512.02444v2 Announce Type: replace-cross Abstract: Joining heterogeneous tables requires different forms of correspondence, including exact agreement, syntactic transformation, semantic similar
arXiv:2610.13278v1 Announce Type: new Abstract: Vision-language models (VLMs) exhibit complementary capabilities, yet selecting the most suitable expert for a given image-question query remains challe
Microsoft Corp. today pulled back the curtains on Maia 300, its newest internally developed artificial intelligence accelerator. The chip is optimized for inference. Microsoft estimates that it can pr
Tom Warren / The Verge: Microsoft unveils its third-gen in-house AI chip, the Maia 300, built on TSMC's N2P process node and aimed at serving as its “primary AI inference system” — The new Maia 300 ch
Microsoft is announcing its third-generation Maia in-house AI chip today, designed to be the 'primary AI inference system' for Microsoft's products and services. Maia 300 not only improves the cost an
arXiv:2610.12881v1 Announce Type: new Abstract: Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world model
arXiv:2610.12575v1 Announce Type: cross Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture tempora