Dhruv Diddi PRO

ddiddi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a paper 15 days ago

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Paper • 2411.02959 • Published 17 days ago • 62

upvoted 3 papers 24 days ago

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published about 1 month ago • 88

Can Knowledge Editing Really Correct Hallucinations?

Paper • 2410.16251 • Published Oct 21 • 54

ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting

Paper • 2410.17856 • Published 30 days ago • 49

upvoted 2 papers 29 days ago

LLM-based Optimization of Compound AI Systems: A Survey

Paper • 2410.16392 • Published Oct 21 • 13

Aligning Large Language Models via Self-Steering Optimization

Paper • 2410.17131 • Published about 1 month ago • 21

upvoted 9 papers about 1 month ago

Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts

Paper • 2410.10626 • Published Oct 14 • 37

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Paper • 2410.10819 • Published Oct 14 • 6

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Paper • 2410.10563 • Published Oct 14 • 37

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Paper • 2410.10306 • Published Oct 14 • 52

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

Paper • 2410.05603 • Published Oct 8 • 11

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

Paper • 2410.05363 • Published Oct 7 • 44

FürElise: Capturing and Physically Synthesizing Hand Motions of Piano Performance

Paper • 2410.05791 • Published Oct 8 • 7

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Paper • 2410.02707 • Published Oct 3 • 48

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1 • 144

upvoted 5 papers 3 months ago

FLUX that Plays Music

Paper • 2409.00587 • Published Sep 1 • 31

Law of Vision Representation in MLLMs

Paper • 2408.16357 • Published Aug 29 • 92

Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

Paper • 2408.15518 • Published Aug 28 • 42

Writing in the Margins: Better Inference Pattern for Long Context Retrieval

Paper • 2408.14906 • Published Aug 27 • 138

LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs

Paper • 2408.13467 • Published Aug 24 • 24