Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow.
arXiv:2608. 07579v1 Announce Type: cross Abstract: The AI City Challenge 2026 Track 1 evaluates multi-camera 3D perception in large indoor warehouses under a synthetic-to-real (Sim2Real) setting; depth is available only for training and validation, so inference is RGB-only.
arXiv:2608. 07663v1 Announce Type: cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs).
arXiv:2608. 07946v1 Announce Type: cross Abstract: Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean.
arXiv:2608. 08009v1 Announce Type: cross Abstract: Fake news increasingly relies on cross-modal image-text forgeries, making transparent and verifiable reasoning chains an urgent need for Detecting and Grounding Multi-Modal Media Manipulation (DGM4).
arXiv:2608. 08219v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios.
arXiv:2608. 08207v1 Announce Type: cross Abstract: Multivariate Time Series Classification (MTSC) demands models that can effectively capture complex temporal patterns across multiple scales while remaining computationally efficient.
arXiv:2608. 08311v1 Announce Type: cross Abstract: We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits that become the runtime for later work.
arXiv:2608. 08479v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing.
arXiv:2608. 08612v1 Announce Type: cross Abstract: Recently, retrieval-augmented and memory-augmented methods have emerged as two promising paradigms for long-video question answering.
arXiv:2608. 08618v1 Announce Type: cross Abstract: Industrial device commissioning requires engineers to manually extract hundreds of protocol-specific parameters from heterogeneous PDF manuals and transcribe them into supervisory control systems, a time-intensive, error-prone workflow.
arXiv:2608. 08721v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically determined by the speculative length selected at each decoding round.
arXiv:2608. 08727v1 Announce Type: cross Abstract: To address this gap, we introduce TomaMMU, a large-scale Tomato leaf disease MultiModal Understanding dataset, alongside TomaBench, a benchmark for evaluating VLMs on tomato disease understanding.
arXiv:2608. 08764v1 Announce Type: cross Abstract: On-policy self-distillation improves language-model reasoning by querying a teacher on states actually visited by the student.
arXiv:2608. 08878v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequence length, creating a severe memory bottleneck for long-context inference.
arXiv:2608. 09221v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed client devices while preserving data privacy.
arXiv:2608. 09228v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory.
arXiv:2608. 09270v1 Announce Type: cross Abstract: Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation.
arXiv:2608. 09285v1 Announce Type: cross Abstract: Learning-based wireless localizers often fail to utilize geometric information about the propagation environment, limiting their ability to exploit non-line-of-sight (NLoS) propagation and generalize across scenes.
arXiv:2608. 09286v1 Announce Type: cross Abstract: Global medium-range weather forecasting requires modeling structured yet state-dependent interactions among heterogeneous atmospheric fields.