Update README.md

README.md

@@ -9,7 +9,7 @@ pinned: false
 
 The Knowledge Engineering Group (**[KEG](https://twitter.com/thukeg)**) & Data Mining ([THUDM](https://github.com/THUDM)) at Tsinghua University. 
 
-We build **LLMs**: 
+We build **LLMs** and related training & inference techniques: 
 
 * **[ChatGLM](https://github.com/THUDM/ChatGLM3)**: Open Bilingual Chat LLMs, among which the ChatGLM-6B series has attracted **10,000,000** downloads on HF. 
 * **[CodeGeeX](https://github.com/THUDM/CodeGeeX2)**: A Multilingual Code Generation Model (KDD 2023)
@@ -18,10 +18,12 @@ We build **LLMs**:
 * **[GLM-130B](https://github.com/THUDM/GLM-130B)**: An Open Bilingual Pre-Trained Model (ICLR 2023)
 * **[CogView](https://github.com/THUDM/CogView)**: An Open Text-to-Image Generation Model (NeurIPS 2021)
 * **[CogVideo](https://github.com/THUDM/CogVideo)**: An Open Text-to-Video Generation Model (ICLR 2023)
+* **[CogAgent](https://github.com/THUDM/CogVLM)**: A Visual Language Model for GUI Agents
 * **[AgentTuning](https://github.com/THUDM/AgentTuning)**: Enabling Generalized Agent Abilities for LLMs
+* **[APAR](https://arxiv.org/abs/2401.06761)**: LLMs Can Do Auto-Parallel Auto-Regressive Decoding
 
 We also work on **LLM evaluations**: 
-* **[AgentBench](https://github.com/THUDM/AgentBench)**: A Benchmark to Evaluate LLMs as Agents
+* **[AgentBench](https://github.com/THUDM/AgentBench)**: A Benchmark to Evaluate LLMs as Agents (ICLR 2024)
 * **[AlignBench](https://github.com/THUDM/AlignBench)**: A Benchmark to Evaluate Chinese Alignment of LLMs
 * **[LongBench](https://github.com/THUDM/LongBench)**: A Bilingual, Multitask Benchmark for Long Context Understanding