127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “evaluation”

41,190 results

Agents

AWM: Answerable Working Memory for Long-Document VQA Agents

DGX agent

arXiv:2608.25618v1 Announce Type: new Abstract: Long-document visual question answering increasingly relies on VLM agents that retrieve candidate pages, inspect page images, write findings to working

agentsarxiv-cs-cl

27 Aug 2026

Model Releases

b10660

DGX agent

model: add Qwen3.8-Flash-Next (qwen4exp) (#27742) gguf: add qwen4exp (Qwen3.8-Flash-Next) arch and converter Adds the GGUF-side plumbing for HF model_type qwen4_exp: MODEL_ARCH.QWEN4EXP plus tensors f

Search: “evaluation”

AWM: Answerable Working Memory for Long-Document VQA Agents

b10660

BanglaMamba: Exploring State Space Models for Bangla Fake News Detection

Bayesian Flow Networks for Offline Trajectory Planning

Belief Cascades Drive Persuasion in LLM Agent Networks

Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward Learning

Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory

Bidirectional Temporal Dynamics Modeling for EEG-based Driving Fatigue Recognition

BRIDLE: Generalized Self-supervised Learning with Quantization

CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery

Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions

Clearing the Underbrush: AI-Enhanced RF Interference Suppression

Cluster-Dags as Powerful Background Knowledge For Causal Discovery

Continually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversion

Control-Oriented Learning for Dynamic Tracking and Stability Analysis of Soft Pneumatic Actuators

Controllable Affective Generation via Latent Vector Steering

Controlling for Omitted Variable Bias in Deep Neural Networks

DataKernelBench: Can LLMs Optimize Database Queries on GPUs?

DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors

DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning

DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction

Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic Segmentation

Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design Interfaces

Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition

Emyx: Fast and efficient all-atom protein generation

EXAONE Tabular 1.0 : Technical Report

Fairness-Aware Test-Time Prompt Tuning

FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference

Fast Generative Grasping via Lie Group-Constrained MeanFlow

FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selection

FRAME: separating sampling variation from representational cause in medical imaging fairness

From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection

From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations

From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers

GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models

GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval

Hierarchical MoE for Multi-Modal ILD Diagnosis

Horus Cyber Nano 1.0

ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing

Infer Human's Intentions Before Following Natural Language Instructions

InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM Guidance

Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching

Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting

Loss-Based Active Learning for Neural Abstractive Summarization

Low-Resolution Perception for Robotic Packing