Search: “benchmark”

arXiv:2607.20425v1 Announce Type: new Abstract: What makes writing 'good' remains a persistent question in literary studies and computational linguistics. We present a two-study investigation of how r

arXiv:2607.21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens. Therefore, a safety guard that watches that answer has to keep up w

arXiv:2607.20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm? We answer with four findings from controlled

arXiv:2607.20543v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling. We study thi

arXiv:2607.20883v1 Announce Type: new Abstract: Recent one-step text-to-image (T2I) models enable efficient image synthesis and provide new opportunities for real-time image editing. However, existing

arXiv:2607.20495v1 Announce Type: new Abstract: Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for cach

mii-llm, an open source AI lab, released Zagreus-0.4B-por, a compact bilingual Portuguese–English language model pretrained entirely from scratch. The model has approximately 400 million parameters an

arXiv:2607.21025v1 Announce Type: new Abstract: In Object Goal Navigation task, existing methods are typically restricted to static and single-floor environments, ignoring cross-floor topologies and d

arXiv:2603.21618v2 Announce Type: replace Abstract: We introduce 4DGS360, a diffusion-free framework for 360^{irc} dynamic object reconstruction from casual monocular video. Existing methods often fai

arXiv:2507.07046v3 Announce Type: replace-cross Abstract: Nowadays, speech emotion recognition (SER) plays a vital role in the field of human-computer interaction (HCI) and the evolution of artificial

arXiv:2607.19599v1 Announce Type: cross Abstract: Existing approaches to frictional contact dynamics typically either modify the Coulomb law to improve numerical robustness or solve the exact law in a

arXiv:2602.09345v3 Announce Type: replace-cross Abstract: AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, eac

The race to build AI infrastructure systems has moved beyond chip specifications into a battle over entire rack-scale platforms, as inference and agentic workloads redefine what counts as a computer.

arXiv:2601.15368v3 Announce Type: replace Abstract: Generative image inpainting can produce realistic results even with large, irregular masks, but existing methods still suffer from two common proble

arXiv:2607.19768v1 Announce Type: new Abstract: Very Large Scale Integration (VLSI) global routing is an NP-hard combinatorial optimization problem requiring signal net assignment across capacity-cons

arXiv:2607.19726v1 Announce Type: new Abstract: Automatic pain localization, which involves identifying the anatomical origin of pain from peripheral physiological signals without patient self-report,

arXiv:2607.19847v1 Announce Type: cross Abstract: Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise i

arXiv:2607.19843v1 Announce Type: cross Abstract: Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug repo

arXiv:2607.19747v1 Announce Type: new Abstract: As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream gen

arXiv:2602.19863v3 Announce Type: replace Abstract: Foundation models are transforming Earth Observation (EO), yet the diversity of EO sensors and modalities makes a single universal model unrealistic

arXiv:2607.18332v2 Announce Type: replace-cross Abstract: Accurate prediction of ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) is important for drug discovery. Most predictors

arXiv:2607.18716v1 Announce Type: new Abstract: Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remain

arXiv:2607.19046v1 Announce Type: new Abstract: On-policy Distillation (OPD) supervises a student model on trajectories sampled from its own policy by minimizing the divergence between the output dist

arXiv:2607.19985v1 Announce Type: new Abstract: Dynamic manufacturing environments require multi-agent systems to coordinate effectively under frequent operational disturbances such as machine failure

arXiv:2607.19115v1 Announce Type: new Abstract: Edit-conditioned 3D scene retrieval pairs a reference 3D room with a natural-language modification and retrieves rooms from a corpus that satisfy the ed

arXiv:2607.19609v1 Announce Type: cross Abstract: In this paper, we study an unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) system, where a UAV enhances the sensing

arXiv:2607.20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can hav

arXiv:2607.19879v1 Announce Type: new Abstract: Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While

TLDR: I (with the help of AI) re-implemented every Blackwell-only kernel (DeepGEMM, FlashInfer sparse-MLA, block-scaled FP8) in Triton, because they simply don't exist for sm89. The performance is 2-3

arXiv:2607.19069v1 Announce Type: new Abstract: Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chain transparency, and carbon accounti

arXiv:2407.08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over trai

arXiv:2607.19919v1 Announce Type: cross Abstract: We propose Diffusion ReRoll, a diffusion-based framework for robotic sequential prediction that enables revisable denoising over horizons. Existing di

arXiv:2607.20232v1 Announce Type: new Abstract: The training of learned inertial odometry depends on dense, high-precision position ground truth from motion capture, visual-inertial odometry or SLAM,

arXiv:2607.20119v1 Announce Type: cross Abstract: We introduce the Directional Kernel Mean Difference (DKMD), a signed statistic for univariate distribution comparison that preserves the direction of

arXiv:2607.20291v1 Announce Type: new Abstract: Real-world fashion search involves interactive retrieval across multiple turns. However, existing multi-turn retrieval methods are built on a restrictiv

arXiv:2604.02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safet

arXiv:2607.20011v1 Announce Type: cross Abstract: Traffic-utilisation measurements for network monitoring are corrupted by additive noise and statistical drift: time-dependent change in the signal's m

arXiv:2607.19932v1 Announce Type: new Abstract: Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language

arXiv:2607.19704v1 Announce Type: new Abstract: Scaling LLM-based applications to millions of users is bottlenecked by the inference cost and latency of modern foundation models. A natural fix is to c

arXiv:2607.19484v1 Announce Type: new Abstract: Real-world collision avoidance is a core motivation for studying the dynamics and control of high sideslip drifting in vehicles, yet the practical benef

arXiv:2607.20092v1 Announce Type: cross Abstract: Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is rele

arXiv:2607.16900v2 Announce Type: replace Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale

arXiv:2607.20019v1 Announce Type: new Abstract: Design rule check (DRC) closure remains a major bottleneck in advanced-node physical design. Although detailed routers are rule-aware, residual design r

arXiv:2607.20293v1 Announce Type: new Abstract: Diffusion policies achieve strong visuomotor control by iteratively denoising action chunks, but repeated denoising makes real-time deployment computati

arXiv:2607.19962v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such

arXiv:2607.19659v1 Announce Type: new Abstract: Time-series foundation models can forecast across heterogeneous domains without task-specific training, but their forecasts are fixed once produced and