Search: “models”

The production of meaning in the processing of natural language

model-releasesarxiv-cs-ai

arXiv:2603.20381v2 Announce Type: replace-cross Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing s

Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory

DGX agent

arXiv:2608.03420v1 Announce Type: new Abstract: Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well under

agentsarxiv-cs-ai

5 Aug 2026

Applications

TQLite: Multi-LLM Jury Guided Distillation for Real-time MQM Translation Quality Evaluation

arXiv:2608.02975v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive performance in MQM-based translation quality (TQ) evaluation, and recent advances in large r

applicationsarxiv-cs-ai

UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search

arXiv:2503.00340v2 Announce Type: cross Abstract: Lightweight models are essential for real-time speech enhancement applications. In recent years, there has been a growing trend toward developing incr

researcharxiv-cs-ai

UniEvo-RS: Omni-Prompt Unified Remote Sensing Segmentation with Representative Exemplar-Driven Prototype Evolution

arXiv:2608.03911v1 Announce Type: new Abstract: Prompt-driven vision-language models (VLMs) hold immense promise for accelerating dense remote sensing (RS) annotation, but static models suffer from se

researcharxiv-cs-cv

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

model-releasesarxiv-cs-ai

arXiv:2608.03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense s

When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning

arXiv:2602.00573v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowled

ZK-SR117: A Chunked Zero-Knowledge Attestation Design for Aggregated Fair-Lending Metrics, with a Control Mapping toward Full SR 11-7 Coverage

arXiv:2608.02664v1 Announce Type: cross Abstract: Deploying ML models in regulated decision-making (credit underwriting, fraud detection, loan approval) requires demonstrating fairness and robustness

safetyarxiv-cs-ai

Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation

arXiv:2608.02505v1 Announce Type: cross Abstract: Can scientific abduction occur without continuous sensorimotor embodiment? Recent arguments in AI and philosophy of science hold that genuine hypothes

Adaptive Quantum Physics-Informed Neural Networks for Differential Equations with Applications to Fluid Dynamics

arXiv:2608.00850v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a versatile approach for solving nonlinear partial differential equations (PDEs), yet achieving

Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

arXiv:2512.04954v3 Announce Type: replace Abstract: We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This a

Automatic LV Localization and Short-Axis Plane Estimation from Arbitrary CMR Slice

arXiv:2608.00145v1 Announce Type: cross Abstract: Accurate estimation of left ventricular (LV) orientation is essential for cardiac magnetic resonance (CMR) imaging and downstream analysis. Existing m

Boosting Generalizable Depth Estimation in Endoscopy by Mixture of Lightweight Experts and Intrinsic Image Alignment

arXiv:2608.00415v1 Announce Type: new Abstract: Depth estimation is a significant task for 3D perception in endoscopic surgeries. However, illumination interference and feature diversity in various en

Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs

arXiv:2608.01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defen

researcharxiv-cs-lg

Applications

CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection

arXiv:2608.01885v1 Announce Type: new Abstract: While deep learning models have achieved state-of-the-art performance in time series anomaly detection, their complex architectures incur substantial in

applicationsarxiv-cs-lg

Characterizing Treatment-Context Medication Evidence Across Clinic Notes and Structured EHR Medication History

arXiv:2608.01570v1 Announce Type: new Abstract: Clinic notes and structured electronic health record (EHR) medication history often contain different medication information. Same-visit disagreement be

researcharxiv-cs-cl

Cost-Effective Automated Judging of Natural-Language Mathematical Proofs

arXiv:2608.00004v1 Announce Type: new Abstract: Grading natural-language mathematical proofs is a recurring cost in evaluating math-reasoning systems, and frontier LLM judges are expensive. We ask whe

CoSynFlow: Conformal Symplectic Neural Flows for Cross-System Prediction of Dissipative Hamiltonian Dynamics

arXiv:2608.00571v1 Announce Type: new Abstract: Learning solution operators for differential equations is a central problem in scientific machine learning. However, many neural operator methods optimi

Local Ai

Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search

arXiv:2608.00078v1 Announce Type: new Abstract: Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: IN

local-aiarxiv-cs-cv

Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression

arXiv:2608.01631v1 Announce Type: new Abstract: KV cache compression is commonly evaluated by final-answer accuracy, implicitly assuming that preserving the answer also preserves the reasoning that su

researcharxiv-cs-cl

EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video Generation

arXiv:2608.02474v1 Announce Type: new Abstract: Audio-driven video generation (A2V) has achieved promising progress in synthesizing temporally coherent and audio-visually aligned videos, yet its infer

Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video

arXiv:2608.01058v1 Announce Type: new Abstract: Artificial Intelligence is increasingly applied to surgical video analysis for phase segmentation, skill assessment, and workflow optimization. A key ch

Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning

arXiv:2608.01917v1 Announce Type: new Abstract: Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates re

From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving

arXiv:2602.10719v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled visual backbones, yet it remains unclear how vis

Fused Bayesian Flow Networks for Dual-Target Molecular Design

arXiv:2608.01007v1 Announce Type: new Abstract: Dual-target drug design aims to generate 3D molecules that can simultaneously interact with two target proteins, offering a promising route for discover

Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI

arXiv:2608.01528v1 Announce Type: new Abstract: Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory

GuideGround: VLM-guided Semantic Understanding and Viewpoint-aware Reasoning for 3D Visual Grounding

arXiv:2608.00518v1 Announce Type: new Abstract: 3D visual grounding aims to localize the target object in a 3D scene from a natural language query, requiring both fine-grained semantic understanding a

Hardware

HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference

arXiv:2608.00577v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have become a dominant architecture for large-scale AI services, yet deploying them over geo-distributed heterogeneous

hardwarearxiv-cs-cl

Illuminating Visual Identity in Universal Multimodal Embeddings

arXiv:2608.01794v1 Announce Type: cross Abstract: Universal Multimodal Embeddings (UMEs) aim to unify various modalities and tasks into a shared representation space. In recent years, this field has w

Instruction-Conditioned Exploration with Asymmetric Reinforcement Learning and Self-Distillation

arXiv:2608.02087v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) with Reinforcement Learning (RL) has become an important tool for improving model capabilities, but the LLM

safetyarxiv-cs-cl

Agents

Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving

arXiv:2512.10739v3 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have expanded the mathematical reasoning frontier through Chain-of-Thought (CoT) techniques and Reinforcement Learning

agentsarxiv-cs-cl

Investigating Social Bias in Narrative Image Generation

arXiv:2608.01780v1 Announce Type: new Abstract: Text-to-image (T2I) generation models are increasingly embedded in applications such as media content creation and education, raising concerns about how

safetyarxiv-cs-cv

MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing

arXiv:2608.00107v1 Announce Type: new Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an in

Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling

arXiv:2608.00732v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject ma

MoCRA: Mixture of Compositional Rank-1 Atoms for 4K All-in-One Video Restoration

arXiv:2608.01829v1 Announce Type: new Abstract: Real-world video arrives hazy, rainy, dark, or noisy, and a deployable restorer faces three demands at once: no degradation label, native 4K output, and

Multiple result sets: How Database Migration Service automates SQL server to PostgreSQL translation

model-releasesgoogle-cloud-ai

In the Medium blog post, 'From MARS to SETOF REFCURSOR: Migrating Multi-Result Stored Procedures to PostgreSQL,' we explored the fundamental architectural differences between SQL Server and PostgreSQL

On the Limits of Support-Preserving Alignment and Bounded Filtering

arXiv:2607.18295v2 Announce Type: replace Abstract: We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability

safetyarxiv-cs-lg

OoO-Spec: Out-of-Order Semantic Speculation for Fast Tool Calling

arXiv:2608.00814v1 Announce Type: new Abstract: LLMs generate tool calls token by token, even though the function choice and argument values can often be predicted in parallel from the request and too

PackingGPT: 3D Packing Agent for Real Furniture in Last-Mile Delivery

arXiv:2608.01427v1 Announce Type: new Abstract: 3D bin packing rectangular items into standardised containers to maximise space utilisation under geometric shipping automation. Loading a furniture pur

Local Ai

PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding

arXiv:2601.02457v2 Announce Type: replace Abstract: Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent

local-aiarxiv-cs-cv

PNEC-Mamba: Prototype-Guided Positive-Negative Evidence Calibration for Hyperspectral Image Classification

arXiv:2608.01910v1 Announce Type: new Abstract: In real-world hyperspectral scenes, pixel representations are often ambiguous due to factors such as spectral similarity, mixed pixels, and local contex

Tutorials

Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers

arXiv:2608.01495v1 Announce Type: new Abstract: Detection transformer models, including DETR and its extensions, learn to output a set of object-level embeddings that can be simultaneously decoded int

tutorialsarxiv-cs-cv

Ranking Image Fusion the Way Humans Do: A Learned Pairwise Preference Metric for Infrared-Visible Fusion Assessment

arXiv:2608.01301v1 Announce Type: new Abstract: Infrared-visible image fusion (IVIF) has no ideal fused reference, so fusion algorithms are routinely ranked by scalar objective metrics that formalize

Real-Time Detection and Repair of LLM Agent Failures

arXiv:2608.02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the stan

Rethinking Video Token Compression with a Global Codebook: Learning Once, Compressing Everywhere

arXiv:2608.01271v1 Announce Type: new Abstract: Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent o

researcharxiv-cs-cv

RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures

arXiv:2608.02200v1 Announce Type: new Abstract: Traffic police gestures are safety-critical perception cues for autonomous driving. A deployable recognizer must infer commands causally from continuous

Self-composing neural operators for high-frequency and multiscale PDE surrogates

arXiv:2508.20650v2 Announce Type: replace Abstract: Addressing the computational challenges of high-frequency and multiscale partial differential equations (PDEs), this work introduces a self-composin

Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation

arXiv:2608.01666v1 Announce Type: new Abstract: However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open q