Update index.md

Author: soujanyaporia

index.md

@@ -15,12 +15,13 @@ logo:
 {% include feature_row_home_img id="logo" type="left" %}
 
 Here are some key research by our lab that got some attention:
-- **Multimodal Representation Learning:** [MISA](https://dl.acm.org/doi/pdf/10.1145/3394171.3413678), [TFN](https://arxiv.org/pdf/1707.07250), [MELD](https://arxiv.org/pdf/1810.02508), [MFN](https://ojs.aaai.org/index.php/AAAI/article/view/12021/11880)
+- **Multimodal Representation Learning:** [One of the first works to show multimodal fusion can be achieved using self-attention - MISA](https://dl.acm.org/doi/pdf/10.1145/3394171.3413678), [TFN](https://arxiv.org/pdf/1707.07250), [MELD](https://arxiv.org/pdf/1810.02508), [MFN](https://ojs.aaai.org/index.php/AAAI/article/view/12021/11880), [Multimodal InfoMax](https://arxiv.org/abs/2109.00412)
 - **Emotion/Sentiment Recognition in Conversations/Context or Other Dialogue System Works:** [DialogueRNN](https://ojs.aaai.org/index.php/AAAI/article/download/4657/4535), [DialogueGCN](https://arxiv.org/pdf/1908.11540), [BC-LSTM](https://aclanthology.org/P17-1081.pdf), [MIME](https://arxiv.org/pdf/2010.01454), [CICERO](https://arxiv.org/pdf/2203.13926)
 - **Text-to-Audio Generative Models:** [Tango](https://dl.acm.org/doi/abs/10.1145/3581783.3612348), [TangoFlux](https://arxiv.org/pdf/2412.21037)
 - **LLM Evaluation:** [InstructEval](https://arxiv.org/pdf/2306.04757), [Reasoning Problems](https://arxiv.org/pdf/2401.09395), [PuzzleVQA and AlgoPuzzleVQA](https://arxiv.org/pdf/2502.01081)
 - **AI Safety:** [Red Teaming](https://arxiv.org/pdf/2308.09662), [Resta](https://arxiv.org/pdf/2402.11746)
 - **Retrieval Augmented Generation:** [CoK](https://arxiv.org/pdf/2305.13269), [Trust-Score](https://arxiv.org/pdf/2409.11242)
+  
 > *Intrigued by our logo? [Read](/assets/images/logo-explanation.pdf) the story behind it.*"
   ![image-center](/assets/images/resources/logo-explanation.png){: .width-paper-image-100 .align-center}