📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。

【ACL 2026 Main】AgentMark: Utility-Preserving Behavioral Watermarking for Agents

[ACL 2026 Main Conference] Paper list for the survey "A Survey of Deep Learning for Geometry Problem Solving"

[ACL 2026] Paper list of Video LLM hallucination. Welcome to Star and Contribute!

Official implementation of ACL 2026 paper, "ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation"

Offical repository for ACL 2026 paper "Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection".

[ACL 2026 main] DGPO: Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities

[ACL 2026 Oral] Official code, UIQ benchmark, and pretrained checkpoints for "Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval" (Yoo et al., Sogang University)

Codebase for "When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges" at ACL 2026 CustomNLP4U

The official implementation for ACL 2026 paper CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models

MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning

[ACL 2026 Findings] How Large Language Models Balance Internal Knowledge with User and Document Assertions

[ACL'26] Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

(ACL 2026 Main) Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents

NeoAraBERT is a state-of-the-art open-source Arabic text-embedding model built on the NeoBERT architecture.

(ACL 2026 Main) LLMSurgeon recovers the pretraining data mixture of any LLM from only its generated text — no weights, no training data. A calibrated domain classifier plus label-shift correction de-blurs biased predictions. Ships with LLMScan, a benchmark on 8 open-source LLMs.

[ACL 2026] benchmark codebase for paper: "GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents"

2nd place solution at MedExact shared task at BioNLP@ACL 2026

Official code release for "Learning to Retrieve User History and Generate User Profiles for Personalized Persuasiveness Prediction" (ACL 2026 Findings)