Knowledge catalogue
arXiv:2610.16041v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable success across a wide range of language tasks. At their core, autoregressive LLMs are conditional
Banger paper from Stanford, Together AI, and colleagues. Why is this an interesting paper? Today's LLM agents must write out every reasoning step as text before they can search, run code, or take acti
arXiv:2506.00482v2 Announce Type: replace Abstract: LLM benchmarks are often treated as coherent measurement units, yet they are heterogeneous collections of instances spanning diverse domains, skills
arXiv:2610.17350v1 Announce Type: new Abstract: We use a frozen frontier vision-language model, GPT-6-Astra, directly as the robot policy on RoboMME, a benchmark of 16 memory-dependent manipulation ta
arXiv:2610.14226v1 Announce Type: new Abstract: Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation. M
arXiv:2610.17190v1 Announce Type: new Abstract: Geographic coordinates are common inputs in applied machine learning, but latitude and longitude describe position rather than the surrounding environme
arXiv:2610.18026v1 Announce Type: new Abstract: Some observation-window-based KV cache compressors use prompt attention to identify important tokens but allocate uniform or predefined budgets across h
arXiv:2610.17926v1 Announce Type: new Abstract: Autoregressive video generation relies on memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-sho
arXiv:2610.18850v1 Announce Type: new Abstract: Collaborative planning under operational constraints is essential for heterogeneous robot teams in large-scale missions. Unmanned Aerial Vehicles (UAVs)
arXiv:2610.16908v1 Announce Type: new Abstract: End-to-end driving requires rich spatiotemporal representations to support scene understanding and trajectory planning under strict latency constraints.
arXiv:2610.17083v1 Announce Type: new Abstract: Large Language Models (LLMs) are predominantly trained on imperative programming languages, and existing work on LLM-based robot programming reflects th
arXiv:2610.15185v1 Announce Type: new Abstract: Test-time memorization of sequential information is a foundational capability for any intelligent system that needs to rapidly store and retrieve data,
arXiv:2610.18556v1 Announce Type: new Abstract: Deep learning for medical image restoration is often constrained by the need for paired training data. Acquiring perfectly registered clean-noisy radiog
arXiv:2610.14691v1 Announce Type: new Abstract: Recent advances in 3D hand-object interaction (HOI) perception have opened new opportunities for learning dexterous robotic skills from human videos. Ho
arXiv:2610.18870v1 Announce Type: new Abstract: We generally perceive that training text-to-image diffusion models requires heavy compute: it is true if we aim at a comprehensive frontier model. This
arXiv:2610.13990v1 Announce Type: new Abstract: Sparse attention visits few keys, yet finding them can still require scoring every key with every indexer head. We introduce DoSA (Dots Sparse Attention
arXiv:2610.16866v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training with generative reward models (GenRM) has become a central recipe for improving large language models (LLMs),
arXiv:2610.16176v1 Announce Type: new Abstract: Situated 3D Question Answering requires models to interpret a 3D scene relative to an agent's pose. Existing methods commonly convey that pose through a
arXiv:2610.16118v1 Announce Type: new Abstract: Hour-long videos, streaming feeds, and movie-length content are pushing vision-language models (VLMs) past their breaking point -- the standard recipe o
arXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded
arXiv:2610.16411v1 Announce Type: new Abstract: Deploying robots in human-shared environments requires deciding not only how to navigate, but also when dedicated social signals are worth emitting. Cla
arXiv:2610.17724v1 Announce Type: cross Abstract: Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across
A practical method for converting Figma theme evidence into an LLM handoff that fits an existing application and preserves accessibility.
arXiv:2610.15595v1 Announce Type: new Abstract: In real-world indoor fire environments, visual degradation severely impairs instruction grounding, waypoint prediction, and long-horizon exploration in
arXiv:2610.16161v1 Announce Type: new Abstract: A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from id
arXiv:2610.16890v1 Announce Type: cross Abstract: We introduce FORGE (Fast On-chip Rotor Generation for Experts), a procedural weight generation system for Sparse Mixture-of-Experts (MoE) inference. R
arXiv:2610.17321v1 Announce Type: cross Abstract: As demand for LLM inference grows and consumer GPUs grow more capable, edge deployment is becoming increasingly attractive. WebGPU is compelling in th
arXiv:2602.03945v2 Announce Type: replace Abstract: Simple row-wise predictors that score each row independently remain competitive with far more expressive architectures on tabular benchmarks, which
arXiv:2505.02712v4 Announce Type: replace Abstract: Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its th
arXiv:2610.18125v1 Announce Type: new Abstract: Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining the
arXiv:2610.17948v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding.
arXiv:2610.15957v1 Announce Type: cross Abstract: Transformer models trained on symbolic music have become remarkably capable. However, it is yet unclear how they represent music structure, and whethe
arXiv:2610.18238v1 Announce Type: new Abstract: Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page
arXiv:2610.17684v1 Announce Type: new Abstract: High-fidelity surgical video generation is increasingly important for surgical education, simulation, and downstream AI training, as conventional simula
arXiv:2610.14971v1 Announce Type: new Abstract: WavePhaseNet introduced frequency-resolved semantic representations, QuantumPhaseNet introduced gauge-covariant phase connections, and ModularPhaseNet m
arXiv:2610.18861v1 Announce Type: cross Abstract: How can we build an agent that thinks beyond human language, yet still acts through it in the external environment? Modern LLM agents still reason and
arXiv:2610.17251v1 Announce Type: new Abstract: Separating Alzheimer's Disease (AD), Parkinson's Disease (PD), and Healthy Controls (HC) using structural MRI remains challenging because disease signat
arXiv:2603.07815v2 Announce Type: replace Abstract: Iterative diffusion generation requires different amounts of model capacity at different token positions. Prior model combinations allocate capacity
I built BitRun because I wanted to run 1-bit ternary LLMs on ordinary laptops without melting my battery, spinning up a dedicated GPU, or wrestling with complex build environments. Right now, BitRun g
ICYMI from yesterday's @dealbook: inference startups are ripping as enterprises continue to adopt AI - @togethercompute's annual bookings hit 1.2 billion as of July - @FireworksAI_HQ crossed 1 billion
arXiv:2610.14810v1 Announce Type: cross Abstract: Enterprise AI agents can execute altered versions of approved actions, concurrently reuse the same permission, or retry operations whose responses wer
arXiv:2610.18669v1 Announce Type: cross Abstract: Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitrar
arXiv:2610.15836v1 Announce Type: cross Abstract: When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category
arXiv:2610.16948v1 Announce Type: new Abstract: Convex relaxations make nonconvex optimization tractable by replacing hard nonconvex problems with convex surrogates that give valid bounds. Yet their d
arXiv:2610.16313v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced robotic manipulation by connecting visual perception and language instructions to action generation. H
arXiv:2610.18289v1 Announce Type: new Abstract: Autoregressive video diffusion models have emerged as a foundation for long-horizon world rollout. However, when extended far beyond their training wind
arXiv:2610.18162v1 Announce Type: new Abstract: On-policy self-distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions
arXiv:2610.15894v1 Announce Type: new Abstract: Large language model (LLM) code-repair systems fix faulty programs by repeatedly generating and testing revisions. Each revision is costly, making the c
arXiv:2512.21326v3 Announce Type: replace Abstract: Applying well-established statistical methods effectively to LLM evals requires consideration of model correlations and prediction noises. Leading e
arXiv:2610.17690v1 Announce Type: cross Abstract: Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed traj
arXiv:2610.16090v1 Announce Type: new Abstract: Deep neural networks are capable of both learning generalizing solutions on natural tasks and memorizing arbitrary mappings. We argue that understanding
arXiv:2610.17866v1 Announce Type: new Abstract: Understanding fluorescence microscopy images is fundamental to automating biological research. However, existing methods typically learn predefined conc
arXiv:2610.17244v1 Announce Type: new Abstract: Fast, high-fidelity molecular generation requires accurate chemical choices and efficient sampling. Chemical building blocks reduce graph size, but make
arXiv:2610.17202v1 Announce Type: new Abstract: Multi-Head Latent Attention (MLA) compresses the KV cache into a latent representation, reducing inference memory and bandwidth. Existing MHA2MLA/TransM
arXiv:2610.14871v1 Announce Type: new Abstract: By predicting future states, latent world models provide rich self-supervision for end-to-end driving, but often inherit dense features from pretrained
arXiv:2610.17603v1 Announce Type: new Abstract: Background: Five-year survival prediction from hematoxylin-and-eosin whole-slide images could support risk stratification, but the task is weakly superv
arXiv:2610.13966v1 Announce Type: new Abstract: Predicting cellular responses to chemical and genetic perturbations is a central test for AI virtual cells, yet many single-cell models reduce each cond
arXiv:2610.18407v1 Announce Type: new Abstract: Diffusion language models reconstruct masked tokens in parallel, offering an alternative to autoregressive generation. Yet their Transformer backbones t
arXiv:2610.16356v1 Announce Type: cross Abstract: We present an overview of R package called exttt{naspaclust}, a tool for spatial fuzzy clustering improvement by hybridising the Fuzzy Geographically
arXiv:2511.19548v2 Announce Type: replace Abstract: Neuroeconomics appears to offer welfare economics an evidential supplement, since neural data may help distinguish choices that express genuine pref