Search: “index”

arXiv:2610.17132v1 Announce Type: new Abstract: Attention-based multiple instance learning (MIL) pools a variable-size bag of instance embeddings into one vector. In batched training, bags are padded

arXiv:2610.15215v1 Announce Type: new Abstract: Nearest-neighbor (NN) search underlies countless robotics algorithms, but many state spaces are not Euclidean: orientations live on SO(2) or SO(3) and p

arXiv:2610.17688v1 Announce Type: new Abstract: Occupancy world models provide a structured, metric representation of future driving scenes, making them a promising basis for end-to-end autonomous dri

arXiv:2610.18333v1 Announce Type: cross Abstract: Random features provide a standard approach to scaling kernel methods to large datasets by approximating the kernel with a finite-dimensional feature

arXiv:2610.18280v1 Announce Type: new Abstract: Advection-diffusion plays an essential role in transport phenomena such as atmospheric and cloud dynamics. Improved forecasting of cloud motion, in turn

arXiv:2610.16347v1 Announce Type: new Abstract: Forward-Forward learning replaces end-to-end backpropagation with local, layer-wise training objectives. Its variants are evaluated primarily by classif

arXiv:2606.15734v2 Announce Type: replace-cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate

arXiv:2610.18729v1 Announce Type: new Abstract: Vision-language models (VLMs) that segment from language must pass the location of the referent to a pixel decoder. The dominant interface compresses it

Startups are built on relationships. That’s why IRL events are a core part of our growth strategy at @lemma_ . We hosted our biggest one yet during @SFTechWeek : The Agent Economy Gala. 400+ founders,

arXiv:2603.28916v2 Announce Type: replace Abstract: Football action-value approaches estimate scoring, possession, or other downstream outcome value; complementary descriptions can characterise how a

Source: whatmodel.sh, an open source AI leaderboard I built (and launched here yesterday). Every point comes from published benchmark results: 22,113 of them across 987 benchmarks, from 1,011 sources,

[UPDATE / RETRACTION: The '100% GTO' claim had a prompt-leakage bug] We patched the repo to pass strictly neutral states, here are the real, honest numbers: • Latency: Still ~2ms (ONNX + Absorbing Mar

arXiv:2610.16735v1 Announce Type: new Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal disti

arXiv:2610.14007v1 Announce Type: new Abstract: A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them clos

Last week we announced that Gemini Enterprise has evolved to make it even simpler to get work done, and introduced the Gemini agent, your new universal agent for work. It's always on and ready to answ

https://preview.redd.it/m5e9anluo8vh1.png?width=1080&format=png&auto=webp&s=4c80687e6fe40036843a97ed8975ce46eaab0662 I am excited to share a project I have been working on during the past few years du

Quartermaster (my local inference manager: one server that swaps llama.cpp, image, audio and video models in and out of VRAM) can now help you server and manage decision models: Auto-discovered. Drop

Hi, I see that vllm released d3 (a family of decision models) and llama.cpp already has support for them. I want to try them out. Are decision models sensitive to quantization? I know that for autocom

Katie Roof / Business Insider: Sources: Decagon, which offers AI customer service agents and was last valued at $4.5B, hired a bank and is in early talks with buyers, including ServiceNow — Buzzy AI a

arXiv:2610.12701v1 Announce Type: new Abstract: Perspectivist NLP has established that annotator positionality shapes labels for subjective tasks, but the field still lacks methods for operationalisin

arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge

arXiv:2412.13844v2 Announce Type: replace-cross Abstract: Retrieval models for recommendation need to account for outcomes such as watch time while searching large item corpora efficiently. We present

arXiv:2610.13406v1 Announce Type: cross Abstract: Forecasting desertification has received far less attention than mapping it. We use a convolutional LSTM (ConvLSTM) trained on ten annual Earth Observ

arXiv:2610.13918v1 Announce Type: cross Abstract: Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplif

arXiv:2610.13851v1 Announce Type: cross Abstract: We establish finite-sample guarantees for conditional diffusion models learned from data and implemented with finitely many denoising steps. Our appro

arXiv:2610.13574v1 Announce Type: new Abstract: Feature selection is a central problem in high-dimensional financial regression, where large numbers of engineered variables and strong correlations amo

arXiv:2610.13812v1 Announce Type: new Abstract: Flow-matching and diffusion models are increasingly used as priors for linear inverse problems, however, most methods are bespoke to one class of trajec

arXiv:2610.12599v1 Announce Type: new Abstract: Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures

Three events, one award, a very respectable 4th place in hot sauce. Our SF Tech Week: → AI Demo Night w/ @ClickHouse + @artie_labs: @imaanxsultan won best demo → @matissemlk took 4th in the Blazel hot

Decision 3.0 now on Core ML 🍎 d3-lite triaging 1,000 pull requests into vllm-sr workgroups, live on an M5 Pro: 0.12 s per PR, 8.3 PRs/s, nothing leaves the Mac ⚡ lite, nano and mini are all converted

One of the biggest historical bottlenecks for training specialized models has been curating ground-truth. This is typically a very labor intensive process done with human supervision. Now frontier mod

Rafe Rosner-Uddin / Financial Times: PitchBook: robotics and physical AI companies have raised ~$48B YTD, as they gather training data from people completing tasks in factories, offices, and homes — ‘

DigUp is a free Mac app that runs Google DeepMind’s new EmbeddingGemma 2 locally over your own files. The model puts text, images, audio and video in one space, so you describe what you remember and l

arXiv:2610.11022v1 Announce Type: cross Abstract: Skillful prediction of biomass-burning activity several days in advance is important for air-quality forecasting and aerosol prediction. Two operation

arXiv:2610.11489v1 Announce Type: new Abstract: Visual instance retrieval often fails when the same object appears at different apparent sizes in the query and gallery. We show that the dominant cause

arXiv:2610.12337v1 Announce Type: cross Abstract: Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting for local anatomy and variatio

arXiv:2610.11845v1 Announce Type: new Abstract: Spin in clinical trials includes reporting practices that distort the presentation of results. This is particularly critical in medicine, where spin is

arXiv:2610.11115v1 Announce Type: new Abstract: The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constr

arXiv:2610.11920v1 Announce Type: new Abstract: For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing pas

arXiv:2610.11364v1 Announce Type: new Abstract: A trained 3D Gaussian Splatting (3DGS) scene ships as a portable parameter array that can be copied, pruned, requantized, or repackaged outside its trai

Disclosure: I work at H2O.ai. We released H2O-Lightning-4B, an open-weight (Apache-2.0) model for the 'decisions API' style of inference that Jev made popular: you send a state plus typed questions (p

Disclosure: I'm the developer. The app is called Citenook. I wanted to ask questions across a few hundred PDFs and notes with Ollama, but every setup I tried either needed a lot of glue code or gave a

i'm pulling out my suit for this Huge shoutout to @imaanxsultan and everyone else for organizing! The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised co

arXiv:2610.10954v1 Announce Type: new Abstract: Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect. We instead learn search control, one specifi

arXiv:2610.12304v1 Announce Type: new Abstract: Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in inter

arXiv:2603.07090v2 Announce Type: replace-cross Abstract: Watermarking joint audio-visual generation supports vendor copyright protection and content provenance. However, independently valid audio and