AI Breakdown
Episodes
arxiv preprint - MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding
19 Jan 2024
Contributed by Lukas
In this episode, we discuss MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding by Hongjie Zhang, Yi Liu, Lu Dong, Yi...
arxiv preprint - Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
18 Jan 2024
Contributed by Lukas
In this episode, we discuss Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model by Lianghui Zhu, Bencheng Liao...
arxiv preprint - Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
17 Jan 2024
Contributed by Lukas
In this episode, we discuss Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models by Asma Ghandeharioun, Avi Caci...
arxiv preprint - Time Travel in LLMs: Tracing Data Contamination in Large Language Models
16 Jan 2024
Contributed by Lukas
In this episode, we discuss Time Travel in LLMs: Tracing Data Contamination in Large Language Models by Shahriar Golchin, Mihai Surdeanu. The paper pr...
arxiv preprint - InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes
12 Jan 2024
Contributed by Lukas
In this episode, we discuss InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes by Mohamad Shahbazi, Liesbeth Claessens, Michael Nieme...
arxiv preprint - A Simple LLM Framework for Long-Range Video Question-Answering
11 Jan 2024
Contributed by Lukas
In this episode, we discuss A Simple LLM Framework for Long-Range Video Question-Answering by Ce Zhang, Taixi Lu, Md Mohaiminul Islam, Ziyang Wang, Sh...
arxiv preprint - Mixtral of Experts
09 Jan 2024
Contributed by Lukas
In this episode, we discuss Mixtral of Experts by Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford,...
arxiv preprint - Weight subcloning: direct initialization of transformers using larger pretrained ones
08 Jan 2024
Contributed by Lukas
In this episode we discuss Weight subcloning: direct initialization of transformers using larger pretrained ones by Mohammad Samragh, Mehrdad Fara...
arxiv preprint - Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
05 Jan 2024
Contributed by Lukas
In this episode we discuss Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task by Maya Okawa, Ekdeep S...
arxiv preprint - LLM in a flash: Efficient Large Language Model Inference with Limited Memory
05 Jan 2024
Contributed by Lukas
In this episode, we discuss LLM in a flash: Efficient Large Language Model Inference with Limited Memory by Keivan Alizadeh, Iman Mirzadeh, Dmitry Bel...
arxiv preprint - The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
02 Jan 2024
Contributed by Lukas
In this episode, we discuss The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction by Pratyusha Sharma, Jor...
arxiv preprint - DreaMoving: A Human Video Generation Framework based on Diffusion Models
29 Dec 2023
Contributed by Lukas
In this episode we discuss DreaMoving: A Human Video Generation Framework based on Diffusion Models by Mengyang Feng, Jinlin Liu, Kai Yu, Yuan Yao...
arxiv preprint - Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
28 Dec 2023
Contributed by Lukas
In this episode we discuss Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution by Mostafa Dehghani, Basil Mustafa, Josi...
arxiv preprint - UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
28 Dec 2023
Contributed by Lukas
In this episode, we discuss UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces by Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehu...
arxiv preprint - LongNet: Scaling Transformers to 1,000,000,000 Tokens
27 Dec 2023
Contributed by Lukas
In this episode we discuss LongNet: Scaling Transformers to 1,000,000,000 Tokens by Jiayu Ding, Shuming Ma, Li Dong, Xingxing Zhang, Shaohan Huang...
arxiv preprint - MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
27 Dec 2023
Contributed by Lukas
In this episode, we discuss MotionCtrl: A Unified and Flexible Motion Controller for Video Generation by Zhouxia Wang, Ziyang Yuan, Xintao Wang, Tians...
arxiv preprint - Model-tuning Via Prompts Makes NLP Models Adversarially Robust
26 Dec 2023
Contributed by Lukas
In this episode we discuss Model-tuning Via Prompts Makes NLP Models Adversarially Robust by Mrigank Raman, Pratyush Maini, J. Zico Kolter, Zachar...
arxiv preprint - Training Chain-of-Thought via Latent-Variable Inference
22 Dec 2023
Contributed by Lukas
In this episode we discuss Training Chain-of-Thought via Latent-Variable Inference by Du Phan, Matthew D. Hoffman, David Dohan, Sholto Douglas, Tu...
arxiv preprint - Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
21 Dec 2023
Contributed by Lukas
In this episode we discuss Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation by Bingxin Ke, Anton Obukhov, Shengyu Huang...
arxiv preprint - Instruction-tuning Aligns LLMs to the Human Brain
20 Dec 2023
Contributed by Lukas
In this episode we discuss Instruction-tuning Aligns LLMs to the Human Brain by Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimp...
arxiv preprint - WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
19 Dec 2023
Contributed by Lukas
In this episode we discuss WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia by Sina J. Sem...
arxiv preprint - DemoFusion: Democratising High-Resolution Image Generation With No $$$
18 Dec 2023
Contributed by Lukas
In this episode we discuss DemoFusion: Democratising High-Resolution Image Generation With No $$$ by Ruoyi Du, Dongliang Chang, Timothy Hospedales...
arxiv preprint - Recommender Systems with Generative Retrieval
15 Dec 2023
Contributed by Lukas
In this episode we discuss Recommender Systems with Generative Retrieval by Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan H. Keshavan, T...
arxiv preprint - Mamba: Linear-Time Sequence Modeling with Selective State Spaces
14 Dec 2023
Contributed by Lukas
In this episode we discuss Mamba: Linear-Time Sequence Modeling with Selective State Spaces by Albert Gu, Tri Dao. The paper presents Mamba, an in...
arxiv preprint - Block-State Transformers
13 Dec 2023
Contributed by Lukas
In this episode we discuss Block-State Transformers by Mahan Fathi, Jonathan Pilault, Orhan Firat, Christopher Pal, Pierre-Luc Bacon, Ross Goroshi...
arxiv preprint - Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
12 Dec 2023
Contributed by Lukas
In this episode we discuss Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns by Brian DuSell, David Chiang. Th...
arxiv preprint - LooseControl: Lifting ControlNet for Generalized Depth Conditioning
11 Dec 2023
Contributed by Lukas
In this episode we discuss LooseControl: Lifting ControlNet for Generalized Depth Conditioning by Shariq Farooq Bhat, Niloy J. Mitra, Peter Wonka....
Announcement: AI Breakdown Youtube Channel
08 Dec 2023
Contributed by Lukas
Welcome back to AI Breakdown! In this special announcement, your hosts Megan and Ray share exciting news - we're expanding to YouTube! This new platfo...
arxiv preprint - OneLLM: One Framework to Align All Modalities with Language
08 Dec 2023
Contributed by Lukas
In this episode we discuss OneLLM: One Framework to Align All Modalities with Language by Jiaming Han, Kaixiong Gong, Yiyuan Zhang, Jiaqi Wang, Ka...
arxiv preprint - The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
08 Dec 2023
Contributed by Lukas
In this episode we discuss The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning by Bill Yuchen Lin, Abhilasha Ravichande...
arxiv - MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
07 Dec 2023
Contributed by Lukas
In this episode, we discuss MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI by Xiang Yue, Yuansheng N...
arxiv preprint - MLP-Mixer: An all-MLP Architecture for Vision
07 Dec 2023
Contributed by Lukas
In this episode we discuss MLP-Mixer: An all-MLP Architecture for Vision by Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiao...
arxiv preprint - Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
06 Dec 2023
Contributed by Lukas
In this episode we discuss Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine by Harsha Nori, Yin Tat Lee,...
arxiv preprint - Nash Learning from Human Feedback
05 Dec 2023
Contributed by Lukas
In this episode we discuss Nash Learning from Human Feedback by Remi Munos, Michal Valko, Daniele Calandriello, Mohammad Gheshlaghi Azar, Mark Rowland...
arxiv preprint - Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
04 Dec 2023
Contributed by Lukas
In this episode we discuss Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation by Li Hu, Xin Gao, Peng Zh...
arxiv preprint - Knowledge is a Region in Weight Space for Fine-tuned Language Models
03 Dec 2023
Contributed by Lukas
In this episode we discuss Knowledge is a Region in Weight Space for Fine-tuned Language Models by Almog Gueta, Elad Venezian, Colin Raffel, Noam ...
arxiv preprint - MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
02 Dec 2023
Contributed by Lukas
In this episode we discuss MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training by Pavan Kumar Anasosalu Vasu, Hadi Pouransa...
arxiv preprint - Simplifying Transformer Blocks
01 Dec 2023
Contributed by Lukas
In this episode we discuss Simplifying Transformer Blocks by Bobby He, Thomas Hofmann. The paper studies the possibility of simplifying standard t...
arxiv - Visual In-Context Prompting
30 Nov 2023
Contributed by Lukas
In this episode, we discuss Visual In-Context Prompting by Feng Li, Qing Jiang, Hao Zhang, Tianhe Ren, Shilong Liu, Xueyan Zou, Huaizhe Xu, Hongyang L...
Arxiv Preprint - GAIA: a benchmark for General AI Assistants
29 Nov 2023
Contributed by Lukas
In this episode we discuss GAIA: a benchmark for General AI Assistants by Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann L...
Arxiv Preprint - DisCo: Disentangled Control for Realistic Human Dance Generation
28 Nov 2023
Contributed by Lukas
In this episode we discuss DisCo: Disentangled Control for Realistic Human Dance Generation by Tan Wang, Linjie Li, Kevin Lin, Yuanhao Zhai, Chung...
Arxiv Preprint - Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
27 Nov 2023
Contributed by Lukas
In this episode we discuss Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation by Eric Zelikman, Eliana Lorch, Lester Mackey,...
Arxiv Preprint - A General Theoretical Paradigm to Understand Learning from Human Preferences
25 Nov 2023
Contributed by Lukas
In this episode we discuss A General Theoretical Paradigm to Understand Learning from Human Preferences by Mohammad Gheshlaghi Azar, Mark Rowland,...
Arxiv Preprint - ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
22 Nov 2023
Contributed by Lukas
In this episode we discuss ShareGPT4V: Improving Large Multi-Modal Models with Better Captions by Lin Chen, Jisong Li, Xiaoyi Dong, Pan Zhang, Con...
ArXiv Preprint - S-LoRA: Serving Thousands of Concurrent LoRA Adapters
21 Nov 2023
Contributed by Lukas
In this episode we discuss S-LoRA: Serving Thousands of Concurrent LoRA Adapters by Ying Sheng, Shiyi Cao, Dacheng Li, Coleman Hooper, Nicholas Le...
ArXiv Preprint - Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities
20 Nov 2023
Contributed by Lukas
In this episode we discuss Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities by AJ Piergiovanni, Isaac Noble...
Arxiv Preprint - LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
17 Nov 2023
Contributed by Lukas
In this episode we discuss LCM-LoRA: A Universal Stable-Diffusion Acceleration Module by Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu, Patrick von Pl...
ArXiv Preprint - Fine-tuning Language Models for Factuality
16 Nov 2023
Contributed by Lukas
In this episode we discuss Fine-tuning Language Models for Factuality by Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning, Chelse...
arxiv preprint - Language Models can be Logical Solvers
15 Nov 2023
Contributed by Lukas
In this episode we discuss Language Models can be Logical Solvers by Jiazhan Feng, Ruochen Xu, Junheng Hao, Hiteshi Sharma, Yelong Shen, Dongyan Zha...
ArXiv Preprint - Prompt Engineering a Prompt Engineer
14 Nov 2023
Contributed by Lukas
In this episode we discuss Prompt Engineering a Prompt Engineer by Qinyuan Ye, Maxamed Axmed, Reid Pryzant, Fereshte Khani. The paper presents PE2...
arxiv preprint - CogVLM: Visual Expert for Pretrained Language Models
13 Nov 2023
Contributed by Lukas
In this episode we discuss CogVLM: Visual Expert for Pretrained Language Models by Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wa...
ArXiv Preprint - De-Diffusion Makes Text a Strong Cross-Modal Interface
10 Nov 2023
Contributed by Lukas
In this episode we discuss De-Diffusion Makes Text a Strong Cross-Modal Interface by Chen Wei, Chenxi Liu, Siyuan Qiao, Zhishuai Zhang, Alan Yuill...
ArXiv Preprint - E3 TTS: Easy End-to-End Diffusion-based Text to Speech
09 Nov 2023
Contributed by Lukas
In this episode we discuss E3 TTS: Easy End-to-End Diffusion-based Text to Speech by Yuan Gao, Nobuyuki Morioka, Yu Zhang, Nanxin Chen. The paper ...
ArXiv Preprint - Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges
08 Nov 2023
Contributed by Lukas
In this episode we discuss Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges by Chenhang Cui, Yiyang Zhou, Xin...
ArXiv Preprint - Learning From Mistakes Makes LLM Better Reasoner
07 Nov 2023
Contributed by Lukas
In this episode we discuss Learning From Mistakes Makes LLM Better Reasoner by Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, W...
ArXiv Preprint - The Generative AI Paradox: ”What It Can Create, It May Not Understand”
06 Nov 2023
Contributed by Lukas
In this episode we discuss The Generative AI Paradox: "What It Can Create, It May Not Understand" by Peter West, Ximing Lu, Nouha Dziri, Faeze Bra...
ArXiv Preprint - TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
03 Nov 2023
Contributed by Lukas
In this episode we discuss TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise by Nan He, Hanyu Lai, Chenyang Zhao...
ArXiv Preprint - MM-VID: Advancing Video Understanding with GPT-4V(ision)
02 Nov 2023
Contributed by Lukas
In this episode we discuss MM-VID: Advancing Video Understanding with GPT-4V(ision) by Kevin Lin, Faisal Ahmed, Linjie Li, Chung-Ching Lin, Ehsan ...
ArXiv Preprint - Zephyr: Direct Distillation of LM Alignment
01 Nov 2023
Contributed by Lukas
In this episode we discuss Zephyr: Direct Distillation of LM Alignment by Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Kashif ...
ArXiv Preprint - ControlLLM: Augment Language Models with Tools by Searching on Graphs
31 Oct 2023
Contributed by Lukas
In this episode we discuss ControlLLM: Augment Language Models with Tools by Searching on Graphs by Zhaoyang Liu, Zeqiang Lai, Zhangwei Gao, Erfei...
ArXiv Preprint - Talk like a Graph: Encoding Graphs for Large Language Models
30 Oct 2023
Contributed by Lukas
In this episode we discuss Talk like a Graph: Encoding Graphs for Large Language Models by Bahare Fatemi, Jonathan Halcrow, Bryan Perozzi. The pap...
arxiv Preprint - AgentTuning: Enabling Generalized Agent Abilities for LLMs
29 Oct 2023
Contributed by Lukas
In this episode we discuss AgentTuning: Enabling Generalized Agent Abilities for LLMs by Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yu...
ArXiv Preprint - Jailbreaking Black Box Large Language Models in Twenty Queries
28 Oct 2023
Contributed by Lukas
In this episode we discuss Jailbreaking Black Box Large Language Models in Twenty Queries by Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed ...
ArXiv Preprint - Matryoshka Diffusion Models
27 Oct 2023
Contributed by Lukas
In this episode we discuss Matryoshka Diffusion Models by Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Josh Susskind, Navdeep Jaitly. The paper introdu...
arxiv Preprint - An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning
26 Oct 2023
Contributed by Lukas
In this episode we discuss An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning by Chen Jin, Ryuta...
arxiv Preprint - Retrieval meets Long Context Large Language Models
25 Oct 2023
Contributed by Lukas
In this episode we discuss Retrieval meets Long Context Large Language Models by Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan ...
arxiv Preprint - Contrastive Prefence Learning: Learning from Human Feedback without RL
24 Oct 2023
Contributed by Lukas
In this episode we discuss Contrastive Prefence Learning: Learning from Human Feedback without RL by Joey Hejna, Rafael Rafailov, Harshit Sikchi, ...
arxiv Preprint - BitNet: Scaling 1-bit Transformers for Large Language Models
23 Oct 2023
Contributed by Lukas
In this episode we discuss BitNet: Scaling 1-bit Transformers for Large Language Models by Hongyu Wang, Shuming Ma, Li Dong, Shaohan Huang, Huaiji...
arxiv Preprint - Automatic Prompt Optimization with ”Gradient Descent” and Beam Search
22 Oct 2023
Contributed by Lukas
In this episode we discuss Automatic Prompt Optimization with "Gradient Descent" and Beam Search by Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee,...
arxiv Preprint - Understanding Retrieval Augmentation for Long-Form Question Answering
21 Oct 2023
Contributed by Lukas
In this episode we discuss Understanding Retrieval Augmentation for Long-Form Question Answering by Hung-Ting Chen, Fangyuan Xu, Shane A. Arora, E...
arxiv Preprint - On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
20 Oct 2023
Contributed by Lukas
In this episode we discuss On the Connection between Pre-training Data Diversity and Fine-tuning Robustness by Vivek Ramanujan, Thao Nguyen, Sewoo...
arxiv Preprint - Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
19 Oct 2023
Contributed by Lukas
In this episode we discuss Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness by Felix Friedrich, Manuel Brack, Lukas Struppe...
arxiv Preprint - In-Context Pretraining: Language Modeling Beyond Document Boundaries
18 Oct 2023
Contributed by Lukas
In this episode we discuss In-Context Pretraining: Language Modeling Beyond Document Boundaries by Weijia Shi, Sewon Min, Maria Lomeli, Chunting Z...
ICCV 2023 - Sigmoid Loss for Language Image Pre-Training
17 Oct 2023
Contributed by Lukas
In this episode we discuss Sigmoid Loss for Language Image Pre-Training by Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer. The pap...
arxiv Preprint - Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
16 Oct 2023
Contributed by Lukas
In this episode we discuss Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading by Howard Chen, Ramakanth Pasunuru, Jaso...
arxiv Preprint - HyperAttention: Long-context Attention in Near-Linear Time
15 Oct 2023
Contributed by Lukas
In this episode we discuss HyperAttention: Long-context Attention in Near-Linear Time by Insu Han, Rajesh Jayaram, Amin Karbasi, Vahab Mirrokni, D...
arxiv Preprint - InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
13 Oct 2023
Contributed by Lukas
In this episode we discuss InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists by Yulu Gan, Sungwoo Park, Alexander...
arxiv Preprint - Large Language Models Cannot Self-Correct Reasoning Yet
12 Oct 2023
Contributed by Lukas
In this episode we discuss Large Language Models Cannot Self-Correct Reasoning Yet by Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng...
arxiv Preprint - Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
11 Oct 2023
Contributed by Lukas
In this episode we discuss Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution by Chrisantha Fernando, Dylan Banarse, Henryk Mic...
arxiv Preprint - Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
10 Oct 2023
Contributed by Lukas
In this episode we discuss Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation by Eric Zelikman, Eliana Lorch, Lester Mackey,...
arxiv Preprint - Improved Baselines with Visual Instruction Tuning
09 Oct 2023
Contributed by Lukas
In this episode we discuss Improved Baselines with Visual Instruction Tuning by Haotian Liu, Chunyuan Li, Yuheng Li, Yong Jae Lee. The authors pro...
arxiv Preprint - Tree of Thoughts: Deliberate Problem Solving with Large Language Models
08 Oct 2023
Contributed by Lukas
In this episode we discuss Tree of Thoughts: Deliberate Problem Solving with Large Language Models by Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Sha...
Neurips 2023 - Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
07 Oct 2023
Contributed by Lukas
In this episode we discuss Evaluating Cognitive Maps and Planning in Large Language Models with CogEval by Ida Momennejad, Hosein Hasanbeig, Felip...
ICCV 2023 - Diffusion Models as Masked Autoencoders
06 Oct 2023
Contributed by Lukas
In this episode we discuss Diffusion Models as Masked Autoencoders by Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, H...
arxiv Preprint - Conditional Diffusion Distillation
05 Oct 2023
Contributed by Lukas
In this episode we discuss Conditional Diffusion Distillation by Kangfu Mei, Mauricio Delbracio, Hossein Talebi, Zhengzhong Tu, Vishal M. Patel, P...
arxiv Preprint - Enable Language Models to Implicitly Learn Self-Improvement From Data
04 Oct 2023
Contributed by Lukas
In this episode we discuss Enable Language Models to Implicitly Learn Self-Improvement From Data by Ziqi Wang, Le Hou, Tianjian Lu, Yuexin Wu, Yun...
arxiv Preprint - Efficient Streaming Language Models with Attention Sinks
03 Oct 2023
Contributed by Lukas
In this episode we discuss Efficient Streaming Language Models with Attention Sinks by Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike L...
Neurips 2023 - PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving
02 Oct 2023
Contributed by Lukas
In this episode we discuss PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving by Sepidehsadat Hosseini, Mohammad Am...
arxiv Preprint - Vision Transformers Need Registers
01 Oct 2023
Contributed by Lukas
In this episode we discuss Vision Transformers Need Registers by Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski. The paper discus...
arxiv Preprint - VPA: Fully Test-Time Visual Prompt Adaptation
30 Sep 2023
Contributed by Lukas
In this episode we discuss VPA: Fully Test-Time Visual Prompt Adaptation by Jiachen Sun, Mark Ibrahim, Melissa Hall, Ivan Evtimov, Z. Morley Mao, ...
arxiv Preprint - Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition
29 Sep 2023
Contributed by Lukas
In this episode we discuss Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition by Yu Yu, Chao-Han Huc...
arxiv Preprint - DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
28 Sep 2023
Contributed by Lukas
In this episode we discuss DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models by Sam Ade Ja...
arxiv Preprint - VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
27 Sep 2023
Contributed by Lukas
In this episode we discuss VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning by Han Lin, Abhay Zala, Jaemin Cho, M...
arxiv Preprint - PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
26 Sep 2023
Contributed by Lukas
In this episode we discuss PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training by Dawei Zhu, Nan Yang, Liang Wang, ...
arxiv Preprint - Summarization is (Almost) Dead
25 Sep 2023
Contributed by Lukas
In this episode we discuss Summarization is (Almost) Dead by Xiao Pu, Mingqi Gao, Xiaojun Wan. The paper investigates the capabilities of large la...
arxiv Preprint - LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent
23 Sep 2023
Contributed by Lukas
In this episode we discuss LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent by Jianing Yang, Xuweiyi Chen, ...
Neurips 2023 spotlight - Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems
22 Sep 2023
Contributed by Lukas
In this episode we discuss Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems by Benjamin Coleman, Wang-Cheng Kang,...
arxiv Preprint - Chain-of-Verification Reduces Hallucination in Large Language Models
21 Sep 2023
Contributed by Lukas
In this episode we discuss Chain-of-Verification Reduces Hallucination in Large Language Models by Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, ...
arxiv Preprint - Language Modeling Is Compression
20 Sep 2023
Contributed by Lukas
In this episode we discuss Language Modeling Is Compression by Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein...
arxiv Preprint - From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
19 Sep 2023
Contributed by Lukas
In this episode we discuss From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting by Griffin Adams, Alexander Fabbri, Faisal La...