Knowledge catalogue
arXiv:2508.13680v5 Announce Type: replace Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) in
arXiv:2609.25731v1 Announce Type: new Abstract: Medium-resolution (10-30 m) burned area mapping is vital for monitoring wildfires and their impacts, but remains difficult to scale. Existing methods re
arXiv:2609.26460v1 Announce Type: new Abstract: Anomaly detection systems are often trained using normal data alone, while model selection and evaluation typically require labeled anomalies. We study
arXiv:2605.11280v2 Announce Type: replace-cross Abstract: Fast surrogate models for expensive simulations are now essential across the sciences, yet they typically operate as black boxes. We present e
arXiv:2609.26034v1 Announce Type: new Abstract: Water treatment research is expanding rapidly, but much of the knowledge acquired from this research remains scattered across unstructured literature. T
arXiv:2609.24662v1 Announce Type: new Abstract: LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume
arXiv:2609.25405v1 Announce Type: cross Abstract: Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suf
arXiv:2609.26751v1 Announce Type: new Abstract: Large language models are increasingly used to generate SystemVerilog Assertions from natural-language specifica- tions and register-transfer-level desi
arXiv:2609.25615v1 Announce Type: new Abstract: Architectural floor plans remain a high-friction barrier to archive digitization and early design-model preparation because heterogeneous graphics encod
arXiv:2609.25373v1 Announce Type: new Abstract: On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or nar
arXiv:2609.25082v1 Announce Type: new Abstract: Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-fro
arXiv:2609.24352v1 Announce Type: new Abstract: Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, a
arXiv:2609.24002v1 Announce Type: new Abstract: Large language model agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specifie
arXiv:2609.25655v1 Announce Type: new Abstract: As large language models (LLMs) scale rapidly, dense full-parameter adaptation becomes increasingly expensive, motivating sparse and modular architectur
arXiv:2609.23130v1 Announce Type: new Abstract: Large language model (LLM) inference is evolving from an engine-local optimization problem into a distributed control problem involving reusable state,
arXiv:2502.02552v2 Announce Type: replace Abstract: This paper proposes a hierarchical Bayesian multitask learning model that is applicable to the general multi-task binary classification learning pro
arXiv:2609.26549v1 Announce Type: new Abstract: Individual tree crown segmentation from aerial imagery underpins tree-level carbon accounting, biodiversity, and restoration monitoring at landscape sca
arXiv:2609.24186v1 Announce Type: new Abstract: Large language models have achieved remarkable progress on Text-to-SQL through reasoning-enhanced fine-tuning, yet existing approaches predominantly rel
arXiv:2609.26177v1 Announce Type: new Abstract: Structured pruning of attention heads provides a hardware-friendly way to compress Transformer language models. However, existing methods for measuring
arXiv:2609.23925v1 Announce Type: cross Abstract: We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, a
arXiv:2609.25745v1 Announce Type: new Abstract: RandOpt samples weight-perturbed language models and ensembles top-ranked candidates through plurality voting, but its global perturbation scale ignores
arXiv:2609.24876v1 Announce Type: new Abstract: In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confide
arXiv:2609.26069v1 Announce Type: cross Abstract: Simulation-based tutor selection can be unstable when predictively adequate learner models imply different policy rankings. RankCert certifies one of
arXiv:2609.25633v1 Announce Type: cross Abstract: Dynamic 3D Gaussian splats (3DGS) model time-varying scenes using a separate Gaussian set per frame. While neighboring video frames are highly correla
arXiv:2609.26210v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to interpret charts and generate natural-language explanations for socially consequential data. Howe
What it is. stuntd is a local proxy for typed LLM decisions: choice, yes/no, score. Your app keeps calling its provider through it. stuntd records the decisions, trains a small head on top of Laya (th
arXiv:2609.22694v1 Announce Type: new Abstract: Public crash databases increasingly support automated safety analysis, but crash severity prediction remains difficult to translate into public-sector d
arXiv:2609.26063v1 Announce Type: new Abstract: Federated graph learning (FGL) enables multiple clients to collaboratively train graph models without sharing their private graph data, providing a prom
arXiv:2609.25775v1 Announce Type: new Abstract: Recent advances in generative video models have enabled the synthesis of visually realistic content, posing significant challenges to synthetic video de
arXiv:2609.26168v1 Announce Type: cross Abstract: Recent work reports that vision--language models (VLMs) struggle to establish and maintain stable reference in repeated reference games. Rather than a
arXiv:2609.26035v1 Announce Type: new Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and ex
arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language mo
arXiv:2609.24698v1 Announce Type: new Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which follo
arXiv:2609.23084v1 Announce Type: new Abstract: Over-the-air federated learning lets edge devices transmit their local updates simultaneously, reducing the communication overhead. The resulting wavefo
Matthias Bastian / The Decoder: Anthropic says Opus 5.5 matches Fable 5.1 “on most tasks” while costing about 40% less to run than Opus 5; Opus 5.5 costs 4/1M input and 20/1M output tokens — Ask about
As part of our efforts to pace the frontier, we’re committed to supporting independent assessments with deep levels of access across training, evaluation, and deployment. That access should enable thi
arXiv:2609.22302v1 Announce Type: new Abstract: Medical vision-language models can propose how urgently a skin lesion should be reviewed, but the local service retains authority to accept or replace t
arXiv:2609.22127v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to draft contractual language, yet conventional accuracy or preference-based evaluations are poorly m
arXiv:2609.24528v1 Announce Type: cross Abstract: Random forests (RFs) predict well but are opaque, whereas single decision trees are interpretable but unstable. Artificial representative trees (ARTs)
arXiv:2609.22222v1 Announce Type: cross Abstract: Large language models can generate executable data-analysis code, but successful execution is not equivalent to a valid official-statistics result. Th
arXiv:2609.24210v1 Announce Type: new Abstract: Building strong chart-to-code systems increasingly relies on reinforcement learning, whose effectiveness depends critically on the quality of the reward
arXiv:2411.10163v3 Announce Type: replace Abstract: Large language models (LLMs) demonstrate remarkable performance across various tasks, prompting researchers to develop diverse evaluation benchmarks
arXiv:2609.24021v1 Announce Type: cross Abstract: Neural operators are data-driven models that learn mappings from inputs that parameterize partial differential equations, such as spatially varying co
I have to say that I am quite impressed by recent progress in LLM use for coding. I've never really bothered setting up a local model. However now that I went trough some real $$ in Claude / gpt token
arXiv:2609.22697v1 Announce Type: new Abstract: Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated s
arXiv:2609.23659v1 Announce Type: new Abstract: Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create
arXiv:2609.24480v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the conve
I've been running FreeToken on my 2x3090 box for a while and ended up maintaining a fork of it. Posting it in case it's useful to anyone else here. Quick context if you haven't used it: FreeToken is a
arXiv:2609.22609v1 Announce Type: new Abstract: Insertion is a fundamental operation in robotic construction assembly, where variations in material properties and assembly conditions make it difficult
arXiv:2609.24197v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates large language model inference by having a lightweight draft model predict future tokens for verification by
arXiv:2609.24974v1 Announce Type: cross Abstract: Agent harnesses, the external systems that mediate model-environment interaction, can substantially improve agent performance, but their gains remain
Impressive paper showing how much the harness changes a coding agent's results. Harnesses do play a huge role in what you are getting out of the models. GPT-5.5 was run inside both Claude Code and Cod
arXiv:2609.22199v1 Announce Type: new Abstract: Transformer-based large language models often suffer from inter-layer parameter redundancy, where functional transformations are redundantly learned acr
arXiv:2609.23516v1 Announce Type: new Abstract: Structural causal models for time series recover contemporaneous and lagged effects, but most methods require complete observation windows and become mi
arXiv:2609.22904v1 Announce Type: new Abstract: Triage in the emergency department (ED) is a sequential decision process that unfolds turn by turn. Existing evaluations of large language models (LLMs)
arXiv:2609.24244v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) fail at fine-grained visual questions less because they cannot reason than because they never see the evidence:
arXiv:2609.24386v1 Announce Type: new Abstract: Childhood stunting remains a major public health concern in Bangladesh and reflects long-term growth failure influenced by child, maternal, household, s
MiMo-V2.6 is 'simply' the best (for now). Despite its simple architecture design it's currently No.1 in the open-weight benchmarks (weighted average). With 'simple,' I mean a classic Grouped Query Att
arXiv:2609.23336v1 Announce Type: new Abstract: Localizing and describing fine-grained differences between near-identical images is a critical yet underexplored capability for multimodal large languag
arXiv:2609.23073v1 Announce Type: new Abstract: Recent advances in natural language processing have led to molecular Large Language Models (LLMs) with strong performance across diverse chemistry tasks