Knowledge catalogue
arXiv:2608.08596v1 Announce Type: new Abstract: Navigation Instruction Generation (NIG) aims to produce step-by-step natural language instructions for navigation guidance. Existing studies primarily t
arXiv:2608.08871v1 Announce Type: new Abstract: This paper addresses autonomous intervention with an underwater vehicle--manipulator system (UVMS) in confined, cluttered, and partially known environme
arXiv:2608.09707v1 Announce Type: cross Abstract: Embedding trained neural networks as surrogates within optimisation problems is an established practice in operations research. The prevailing approac
arXiv:2608.07585v1 Announce Type: new Abstract: Long-video understanding requires models to efficiently acquire and reuse sparse visual evidence from long and redundant video streams. Recent video too
arXiv:2608.00326v2 Announce Type: replace Abstract: Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields includ
arXiv:2608.08146v1 Announce Type: new Abstract: The increasing complexity of enterprise business scenarios has promoted the widespread adoption of long SKILL documents in agent systems, posing new cha
For organizations deploying AI agents at scale, there’s often a critical divide between structured and unstructured data. While large language models (LLMs) excel at parsing text documents, emails, an
arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.2 billion activated per token. Each spar
arXiv:2608.09575v1 Announce Type: new Abstract: Hyperspectral object tracking leverages abundant spectral information to provide unique advantages for target discrimination in complex scenes. However,
arXiv:2608.07541v1 Announce Type: cross Abstract: Transforming raw neuroimage archives into analysis-ready derivatives relies on three brittle stages: data standardization, modality-specific preproces
NVIDIA Nemotron 3.5 Lightning is an open‑source mixture‑of‑experts language model totaling 30 B parameters with only 3 B active during inference, designed to serve high‑volume, low‑latency execution f
arXiv:2608.09914v1 Announce Type: cross Abstract: Hardware assurance relies on scanning electron microscopy (SEM) to verify nanoscale structures, but assembling the large, high-quality datasets requir
River AI Inc., a startup that helps enterprises customize open-source artificial intelligence models, has raised 1.1 billion in early-stage funding. The company stated in today’s announcement that it
I am working on an AI for a small single-player merge puzzle and would appreciate pointers to related algorithms, papers, or existing implementations. It resembles 2048 in its action -> afterstate ->
arXiv:2608.09629v1 Announce Type: new Abstract: Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artif
arXiv:2604.01029v2 Announce Type: replace-cross Abstract: Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced by a first, are widely assumed to derive their gai
arXiv:2608.08081v1 Announce Type: cross Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneo
arXiv:2608.09196v1 Announce Type: new Abstract: Most existing vision-language navigation tasks assume that instructions are complete and unambiguous. However, real-world robots often encounter natural
arXiv:2608.08746v1 Announce Type: new Abstract: Prospective daily symptom tracking is central to premenstrual health assessment, but repeated ordinal forms impose substantial response burden. We formu
arXiv:2608.09771v1 Announce Type: new Abstract: Vision-language-action policies rely on large multimodal backbones to jointly perform perception, language conditioning, and action generation at every
arXiv:2608.07712v1 Announce Type: cross Abstract: A predictive model receives a self-supervised signal whenever the consequence of an action is observed. Using that signal after deployment is difficul
arXiv:2608.08702v1 Announce Type: new Abstract: Fine-grained facial expression recognition (FER) hinges on capturing subtle muscular cues that distinguish adjacent emotions. Yet capturing these cues p
arXiv:2608.07617v1 Announce Type: new Abstract: Scientific and technical writing depends on markup sources that must compile: LaTeX, Typst, and Markdown pipelines fail on missing delimiters, mismatche
arXiv:2608.07528v1 Announce Type: new Abstract: Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction. The
arXiv:2608.08239v1 Announce Type: cross Abstract: LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents
arXiv:2608.08910v1 Announce Type: new Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales. Tying the scales to a fixed ratio of three collapses
arXiv:2504.20114v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require
arXiv:2608.09052v1 Announce Type: cross Abstract: Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA. H
arXiv:2608.09730v1 Announce Type: new Abstract: Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicit
arXiv:2608.08471v1 Announce Type: new Abstract: Deployed LLM safety guardrails are predominantly static: trained once and frozen at release, while new jailbreak techniques and previously un-addressed
arXiv:2608.08060v1 Announce Type: new Abstract: Fine-tuning vision-language models such as CLIP typically requires backpropagation (BP) through the full model, which is infeasible when only forward-pa
A downside with VLM-based parsing is that they’re generally slower than text-based heuristic approaches. As a result they add latency to any ad-hoc file processing *in-the agent loop* (e.g. if you upl
arXiv:2608.06694v1 Announce Type: new Abstract: Coarse-grained (CG) molecular dynamics extends polymer simulation beyond the scales accessible to all-atom (AA) methods, but bottom-up CG modeling is la
arXiv:2607.10439v3 Announce Type: replace-cross Abstract: We present a physics-inspired classical digital twin of brain-computer- interface (BCI) data: a graph neural network constrained to a band-str
arXiv:2608.06699v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environm
arXiv:2608.07346v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of d
arXiv:2603.20986v2 Announce Type: replace Abstract: Phase-field modeling links thermodynamics and kinetics to microstructural evolution, but multiphysics frameworks such as MOOSE require expertise to
arXiv:2608.07038v1 Announce Type: cross Abstract: Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing
arXiv:2608.06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherently iterative: each action reshapes
I've been comparing Cline / Kilo / Qwen Code lately since they all handle long-task state differently. Cline: has Focus Chain, a markdown file kept outside the conversation that gets reinjected on a c
arXiv:2608.06938v1 Announce Type: cross Abstract: The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reas
arXiv:2608.07430v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mech
arXiv:2608.06808v1 Announce Type: new Abstract: The Automatic Construction of Portfolios via Large Language Models (LLM-ACP) suffers from poor generalization in practical few-shot scenarios when solvi
arXiv:2608.07400v1 Announce Type: new Abstract: Financial question answering is typically evaluated by answer correctness, yet in SEC filings a plausible and even numerically correct answer can be gro
Between chaotic levels of market fragmentation and economic volatility, marketing and communications agencies can no longer rely on the human intuition they’ve traditionally used to win clients and op
arXiv:2608.06803v1 Announce Type: cross Abstract: Ising machines are emerging as promising hardware for combinatorial optimization. With recent advances in CMOS Ising technology, they are becoming att
arXiv:2608.06748v1 Announce Type: cross Abstract: Probabilistic long-term time-series forecasting commonly relies on trained models. Training-free conformal methods typically construct intervals aroun
arXiv:2506.07136v2 Announce Type: replace Abstract: First-frame-conditioned video autoencoders represent a clip with persistent content and a compact motion code. Although this removes much of the app
Meta released Muse Glimmer, a 30‑billion‑parameter dense language model with a context window exceeding 120 K tokens, designed for local, long‑running agentic AI workloads. The model is optimized to r
arXiv:2608.07468v1 Announce Type: new Abstract: World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods requir
arXiv:2608.06741v1 Announce Type: new Abstract: Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales. For equilibrium reasoni
The past week I've been running DSv4 inference on my laptop by keeping everything RAM-resident except the MXFP4-experts (since expert pool is ~147GB and won't fit) TL;DR - read speed is the limiter mo
LiteParse can now extract structured data from your PDF in milliseconds: ✅ checkbox states ✅ annotations ✅ vector graphics ✅ word-level bounding boxes It is the most comprehensive, accurate (and fast)
arXiv:2608.06008v1 Announce Type: new Abstract: Large video diffusion models provide rich spatiotemporal priors for autonomous driving, but existing world-action models often inherit the cost of itera
arXiv:2608.05255v1 Announce Type: cross Abstract: Retail investors lack access to the kind of personalized, tax-aware portfolio management that institutional clients take for granted -- existing robo-
arXiv:2608.06059v1 Announce Type: new Abstract: With the rapid growth of Earth observation technologies, remote sensing archives are rapidly expanding, making remote sensing image-text retrieval (RS-I
arXiv:2608.05832v1 Announce Type: new Abstract: Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination
arXiv:2608.05744v1 Announce Type: new Abstract: Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of ex
arXiv:2608.06301v1 Announce Type: new Abstract: As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts,
Live now: our Local AI Track from AI Engineer World's Fair 2026, brought to you by @nvidia. Thesis: frontier intelligence is becoming something you own. https://www.youtube.com/watch?v=KB41dTlX1Uc&lis