acl2026

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

📚 Read a top-tier AI paper in 5 minutes.

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

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

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

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".

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

[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)

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

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

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

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

EVM-QuestBench — ACL 2026 Long Paper benchmark for execution-grounded natural-language transaction code generation on EVM.

LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation (ACL 2026)

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

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

[ACL 2026 Oral] Official PyTorch Implementation of "Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics"

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

[ACL 2026 Main] MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

[ACL 2026 Main] Automated creativity evaluation of LLMs across open-ended tasks via semantic entropy and multi-agent judging.