Research November 25, 2024 SAMURAI:Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory Abstract
Research November 09, 2024 OpenCoder The Open Cookbook for Top-Tier Code Large Language Models Abstract
Research November 09, 2024 Mixture-of-Transformers:A Sparse and Scalable Architecture for Multi-Modal Foundation Models Abstract
Research October 28, 2024 MrT5:Dynamic Token Merging for Efficient Byte-level Language Models Abstract
Research October 21, 2024 A Theoretical Understanding of Chain-of-Thought:Coherent Reasoning and Error-Aware Demonstration Abstract
Research October 17, 2024 Looking Inward:Language Models Can Learn About Themselves by Introspection Abstract
Research October 16, 2024 Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models Abstract
Research October 14, 2024 Thinking LLMs:General Instruction Following with Thought Generation Abstract
Research October 09, 2024 MLE-bench:Evaluating Machine Learning Agents on Machine Learning Engineering Abstract
Research October 09, 2024 One Initialization to Rule them All:Fine-tuning via Explained Variance Adaptation Abstract
Research October 07, 2024 GSM-Symbolic:Understanding the Limitations of Mathematical Reasoning in Large Language Models Abstract
Research September 30, 2024 Logic-of-Thought. Injecting Logic into Contexts for Full Reasoning in Large Language Models Abstract
Research September 26, 2024 Diffusion-based Visual Foundation Model for High-quality Dense Prediction Abstract
Research September 26, 2024 Logic-of-Thought. Injecting Logic into Contexts for Full Reasoning in Large Language Models Abstract
Research September 25, 2024 VPTQ-Extreme Low-bit Vector Post-Training Quantization for Large Language Models Abstract
Research September 20, 2024 Michelangelo-Long Context Evaluations Beyond Haystacks via Latent Structure Queries Abstract
Research September 20, 2024 LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench Abstract
Research September 19, 2024 Training Language Models to Self-Correct via Reinforcement Learning Abstract
Research September 10, 2024 LLaMA-Omni - Seamless Speech Interaction with Large Language Models Abstract
Research September 10, 2024 GroUSE - A Benchmark to Evaluate Evaluators in Grounded Question Answering Abstract
Research September 06, 2024 Open MAGVIT2 - An Open-Source Project Toward Democratizing Auto-regressive Visual Generation Abstract
Research September 06, 2024 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers Abstract
Research August 20, 2024 Automating Thought of Search - A Journey Towards Soundness and Completeness Abstract
Research August 20, 2024 Transfusion - Predict the Next Token and Diffuse Images with One Multi-Modal Model Abstract
Research August 12, 2024 MoMa - Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts Abstract
Research August 06, 2024 Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Abstract
Research August 06, 2024 Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Abstract
Research August 06, 2024 Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Abstract
Research July 22, 2024 Stretching Each Dollar- Diffusion Training from Scratch on a Micro-Budget Abstract
Research July 07, 2024 Selective Reflection-Tuning, Student-Selected Data Recycling for LLM Instruction-Tuning Abstract
Research June 25, 2024 Data curation via joint example selection further accelerates multimodal learning Abstract
Research June 20, 2024 Connecting the Dots - LLMs can Infer and Verbalize Latent Structure from Disparate Training Data Abstract
Research June 13, 2024 Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B Monte Carlo Trees with Llama-3 8B solve mathematics limitations of LLMs
Research June 13, 2024 Depth Anything V2 Samba architecture achieves 3.73x faster throughput with enhanced context
Research June 11, 2024 Samba - Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling Samba architecture achieves 3.73x faster throughput with enhanced context
Research May 16, 2024 Chameleon - Mixed-Modal Early-Fusion Foundation Models Chameleon integrates images and text, achieving state-of-the-art performance.
Research May 16, 2024 CAT3D - Create Anything in 3D with Multi-View Diffusion Models CAT3D generates high-quality 3D content quickly with multi-view diffusion models.
Research May 15, 2024 LoRA Learns Less and Forgets Less LoRA compared to full finetuning, shows strong regularization effects..
Research January 04, 2022 Deep Learning Interviews - Hundreds of fully solved job interview questions from a wide range of key topics in AI Deep Learning Interview: the best preparation book for AI/ML job seekers and students. Free on ArXiv.
