These are recordings of the latest pieces of breakthrough research on deep learning for NLP and vision. The goal is to put up at least one update per week.

HomePage: https://sites.google.com/view/manishg/
LinkedIn: https://www.linkedin.com/in/manishsgupta/

Manish Gupta is a Principal Applied Researcher at Microsoft India R&D Private Limited at Hyderabad, India. He is also an Adjunct Faculty at IIIT, Hyderabad and a visiting faculty at ISB, Hyderabad. He received his Masters in Computer Science from IIT Bombay (2007) and Ph.D. from the Univ of Illinois at Urbana-Champaign in 2013. He worked for Yahoo! Bangalore from 2005-07. His research interests are in the areas of deep learning, natural language processing, web mining and data mining. He has published 150+ research papers in reputed refereed journals and conferences. He has also co-authored two books: one on Outlier Detection for Temporal Data and another one on Information Retrieval with Verbose Queries.


#256 AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
20:34
#256 AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
#255 Microsoft Phi4 reasoning models
13:20
#255 Microsoft Phi4 reasoning models
#254 Measuring Cultural Bias in Large Language Models
20:03
#254 Measuring Cultural Bias in Large Language Models
#253 Search o1: Agentic Search-Enhanced Large Reasoning Models
18:35
#253 Search o1: Agentic Search-Enhanced Large Reasoning Models
#252 Persuading LLMs to Jailbreak them
21:11
#252 Persuading LLMs to Jailbreak them
#251 Aya Model: An Instruction Finetuned Open-Access Multilingual LM
12:29
#251 Aya Model: An Instruction Finetuned Open-Access Multilingual LM
#250 Can LLMs learn synthetic languages equally well?
13:11
#250 Can LLMs learn synthetic languages equally well?
#249 Visual Autoregressive Modeling
14:06
#249 Visual Autoregressive Modeling
#248 Graph of thoughts
18:36
#248 Graph of thoughts
#247 Rho-1: Not All Tokens Are What You Need for Pretraining
14:45
#247 Rho-1: Not All Tokens Are What You Need for Pretraining
#246 Llama 4 herd of models
12:02
#246 Llama 4 herd of models
#245 PRISM Alignment Dataset for LLMs
27:32
#245 PRISM Alignment Dataset for LLMs
#243 Microsoft Phi4
20:16
#243 Microsoft Phi4
#244 Large Language Models are Human-like Annotators.
1:00:55
#244 Large Language Models are Human-like Annotators.
#242 DeepSeek-V3
32:36
#242 DeepSeek-V3
#241 Can humans learn from debates between LLMs?
20:15
#241 Can humans learn from debates between LLMs?
#240 DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
20:59
#240 DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
#239 Stealing part of a production language model
31:49
#239 Stealing part of a production language model
#238 VideoPoet: An LLM for Zero-Shot Video Generation
22:08
#238 VideoPoet: An LLM for Zero-Shot Video Generation
#237 MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings
19:13
#237 MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings
#236 PLAID: An efficient engine for late interaction retrieval
18:55
#236 PLAID: An efficient engine for late interaction retrieval
#235 ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
17:57
#235 ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
#234 MatFormer: Nested Transformer for Elastic Inference
13:20
#234 MatFormer: Nested Transformer for Elastic Inference
#233 Stable Diffusion 3 and MM-DiT: Rectified flow transformers for high-resolution image synthesis
20:22
#233 Stable Diffusion 3 and MM-DiT: Rectified flow transformers for high-resolution image synthesis
#232 Genie: Generative interactive environments
14:46
#232 Genie: Generative interactive environments
#231 AlphaFold Part 2
29:55
#231 AlphaFold Part 2
#230 AlphaFold Part 1
59:55
#230 AlphaFold Part 1
#229 MiniCPM-V: A GPT-4V Level MLLM on Your Phone
21:11
#229 MiniCPM-V: A GPT-4V Level MLLM on Your Phone
#228 ChapVidMR: Chapter-based Video Moment Retrieval using Natural Language Queries
22:26
#228 ChapVidMR: Chapter-based Video Moment Retrieval using Natural Language Queries
#227 Neural Corpus Indexer for Document Retrieval
19:26
#227 Neural Corpus Indexer for Document Retrieval