AI Breakdown

arxiv preprint - sDPO: Don’t Use Your Data All at Once

In this episode, we discuss sDPO: Don't Use Your Data All at Once by Dahyun Kim, Yungi Kim, Wonho Song, Hyeonwoo Kim, Yunsu Kim, Sanghoon Kim, Chanjun Park. The paper introduces stepwise DPO (sDPO), a novel technique for better aligning large language models (LLM) with human preferences by utilizing preference datasets in stages rather than all at once. sDPO improves upon the direct preference optimization (DPO) process by employing progressively aligned reference models throughout training. The results showed that models trained using sDPO outperformed larger, more parameter-heavy LLMs, demonstrating the effectiveness of this stepwise approach.

arxiv preprint - LITA: Language Instructed Temporal-Localization Assistant

In this episode, we discuss LITA: Language Instructed Temporal-Localization Assistant by De-An Huang, Shijia Liao, Subhashree Radhakrishnan, Hongxu Yin, Pavlo Molchanov, Zhiding Yu, Jan Kautz. The paper introduces the Language Instructed Temporal-Localization Assistant (LITA), which tackles the issue of temporal localization in Large Language Models (LLMs) processing video content, where they struggle to identify "when" an event occurs in a video. LITA incorporates time tokens for better temporal representation, uses a SlowFast token architecture for finer temporal resolution, and emphasizes training on temporal localization data, introducing a new task with its dataset (ActivityNet-RTL). The implementation of LITA demonstrates strong performance improvements in temporal localization tasks and video-based text generation, with the code available on GitHub for public use.

arxiv preprint - AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks

In this episode, we discuss AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks by Max Ku, Cong Wei, Weiming Ren, Harry Yang, Wenhu Chen. This paper presents AnyV2V, a framework that simplifies video-to-video editing by breaking it down into two main steps. It leverages existing image editing models to edit individual frames and then uses a temporally coherent transformation to create a new video. The framework is designed to be versatile and does not require any additional training, allowing it to meet a broad range of user requirements for video editing.

arxiv preprint - InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding

In this episode, we discuss InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding by Yi Wang, Kunchang Li, Xinhao Li, Jiashuo Yu, Yinan He, Guo Chen, Baoqi Pei, Rongkun Zheng, Jilan Xu, Zun Wang, Yansong Shi, Tianxiang Jiang, Songze Li, Hongjie Zhang, Yifei Huang, Yu Qiao, Yali Wang, Limin Wang. InternVideo2 is a cutting-edge video foundation model designed to understand and generate video content, achieving superior performance across multiple video and audio tasks. The training involves a progressive strategy that combines multiple learning techniques and emphasizes the connection between video and text, enhanced through semantic segmentation and the generation of captions. The model's capabilities were proven through rigorous testing, displaying exceptional proficiency in video captioning, dialogue, and understanding of extended video sequences.

arxiv preprint - Giraffe: Adventures in Expanding Context Lengths in LLMs

In this episode, we discuss Giraffe: Adventures in Expanding Context Lengths in LLMs by Arka Pal, Deep Karkhanis, Manley Roberts, Samuel Dooley, Arvind Sundararajan, Siddartha Naidu. The paper reviews techniques for overcoming the fixed context length limitation in large language models like LLaMA or LLaMA 2 by modifying positional encodings and introduces a new truncation strategy. It presents three novel tasks for evaluation, finding that linear scaling of contexts at evaluation time improves model performance, especially with a truncated positional basis. The researchers release new models named Giraffe with extended context lengths, along with datasets and code on HuggingFace to encourage further exploration in context length extrapolation.

arxiv preprint - Explorative Inbetweening of Time and Space

In this episode, we discuss Explorative Inbetweening of Time and Space by Haiwen Feng, Zheng Ding, Zhihao Xia, Simon Niklaus, Victoria Abrevaya, Michael J. Black, Xuaner Zhang. The paper presents a method for generating video sequences from just a starting and ending frame, called bounded generation, by utilizing a new sampling strategy named Time Reversal Fusion. This strategy merges the forward and backward denoising processes guided by the start and end frames to create videos that naturally transition between the two given frames, enable smooth inbetweening of motion, and create looping videos when the frames are the same. Time Reversal Fusion is shown to outperform previous methods in terms of generating complex movements and 3D-consistent visuals without additional training on a model.

arxiv preprint - Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

In this episode, we discuss Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking by Eric Zelikman, Georges Harik, Yijia Shao, Varuna Jayasiri, Nick Haber, Noah D. Goodman. The paper presents Quiet-STaR, an advancement of Self-Taught Reasoner (STaR), which teaches Language Models to generate internal rationales to enhance text predictions. By introducing a tokenwise parallel sampling algorithm, learnable tokens for marking thoughts, and extending teacher-forcing, the approach addresses practical challenges in model implementation. Results demonstrate that the approach enables the model to better predict challenging tokens, answer complex questions, and improve performance on benchmarks without task-specific fine-tuning, signifying progress towards more generative and scalable reasoning in LMs.

arxiv preprint - Evaluating Large Language Models at Evaluating Instruction Following

In this episode, we discuss Evaluating Large Language Models at Evaluating Instruction Following by Zhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng, Tanya Goyal, Danqi Chen. This paper examines the effectiveness of using large language models (LLMs) to evaluate the performance of other models in following instructions, and introduces a new meta-evaluation benchmark called LLM-BAR. The benchmark consists of 419 pairs of texts, with one text in each pair following a given instruction and the other not, designed to challenge the evaluative capabilities of LLMs. The findings show that LLM evaluators vary in their ability to judge instruction adherence and suggest that even the best evaluators need improvement, with the paper proposing new prompting strategies to enhance LLM evaluator performance.

arxiv preprint - Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation

In this episode, we discuss Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation by Se-eun Yoon, Zhankui He, Jessica Maria Echterhoff, Julian McAuley. The paper presents a new protocol with five tasks to assess the performance of synthetic users, generated by large language models, aiming to mimic human behavior in conversational recommender systems. The tasks evaluate essential features such as discussing items, stating preferences, asking for recommendations, and providing feedback. Initial evaluations show that these tasks can identify how language models differ from actual human behavior and suggest how model tuning and prompting can improve the synthetic users' resemblance to real users.

arxiv preprint - Branch-Solve-Merge Improves Large Language Model Evaluation and Generation

In this episode, we discuss Branch-Solve-Merge Improves Large Language Model Evaluation and Generation by Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, Xian Li. The paper introduces the BRANCH-SOLVE-MERGE (BSM) method for improving Large Language Models (LLMs). This method enhances task planning and coherence in LLMs by breaking tasks into sub-tasks, solving them separately, and then combining the solutions. BSM has shown significant improvements in response evaluation and constrained text generation, including better alignment with human judgment, reduced biases, and higher constraint satisfaction.