Can Large Language Models Understand Context?
Paper
•
2402.00858
•
Published
•
20
AI Paper of the Day
A collection of papers that I think are interesting, one added each day
-
-
OLMo: Accelerating the Science of Language Models
Paper • 2402.00838 • Published • 74 -
Self-Rewarding Language Models
Paper • 2401.10020 • Published • 135 -
SemScore: Automated Evaluation of Instruction-Tuned LLMs based on Semantic Textual Similarity
Paper • 2401.17072 • Published • 22 -
TrustLLM: Trustworthiness in Large Language Models
Paper • 2401.05561 • Published • 62 -
Lumiere: A Space-Time Diffusion Model for Video Generation
Paper • 2401.12945 • Published • 82 -
PALP: Prompt Aligned Personalization of Text-to-Image Models
Paper • 2401.06105 • Published • 46 -
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Paper • 2401.10891 • Published • 53 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 46 -
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
Paper • 2402.05140 • Published • 18 -
In-Context Principle Learning from Mistakes
Paper • 2402.05403 • Published • 12 -
Self-Discover: Large Language Models Self-Compose Reasoning Structures
Paper • 2402.03620 • Published • 102 -
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Paper • 2402.07456 • Published • 38 -
Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
Paper • 2311.05657 • Published • 26 -
Premise Order Matters in Reasoning with Large Language Models
Paper • 2402.08939 • Published • 23 -
Chain-of-Thought Reasoning Without Prompting
Paper • 2402.10200 • Published • 90 -
World Model on Million-Length Video And Language With RingAttention
Paper • 2402.08268 • Published • 33 -
How to Train Data-Efficient LLMs
Paper • 2402.09668 • Published • 33 -
Reformatted Alignment
Paper • 2402.12219 • Published • 15 -
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Paper • 2401.16380 • Published • 45 -
LLM Agents can Autonomously Hack Websites
Paper • 2402.06664 • Published • 3 -
VideoPrism: A Foundational Visual Encoder for Video Understanding
Paper • 2402.13217 • Published • 18 -
Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models
Paper • 2402.13064 • Published • 45 -
Genie: Generative Interactive Environments
Paper • 2402.15391 • Published • 67 -
When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
Paper • 2402.17193 • Published • 23 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 564 -
Instruction-tuned Language Models are Better Knowledge Learners
Paper • 2402.12847 • Published • 25 -
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Paper • 2403.00522 • Published • 40 -
AtomoVideo: High Fidelity Image-to-Video Generation
Paper • 2403.01800 • Published • 18 -
Design2Code: How Far Are We From Automating Front-End Engineering?
Paper • 2403.03163 • Published • 92 -
Recovering the Pre-Fine-Tuning Weights of Generative Models
Paper • 2402.10208 • Published • 6 -
A Closer Look at the Limitations of Instruction Tuning
Paper • 2402.05119 • Published • 5 -
Multi-LoRA Composition for Image Generation
Paper • 2402.16843 • Published • 28 -
Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Paper • 2402.19479 • Published • 30 -
Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
Paper • 2403.02677 • Published • 16 -
VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models
Paper • 2403.05438 • Published • 14 -
Stealing Part of a Production Language Model
Paper • 2403.06634 • Published • 85 -
Synth^2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
Paper • 2403.07750 • Published • 19 -
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect
Paper • 2403.03853 • Published • 61 -
Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts
Paper • 2403.08268 • Published • 15 -
GiT: Towards Generalist Vision Transformer through Universal Language Interface
Paper • 2403.09394 • Published • 25 -
Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress
Paper • 2402.19472 • Published • 2 -
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Paper • 2403.09611 • Published • 119 -
Simple and Scalable Strategies to Continually Pre-train Large Language Models
Paper • 2403.08763 • Published • 48 -
Enhancing Vision-Language Pre-training with Rich Supervisions
Paper • 2403.03346 • Published • 12 -
VideoMamba: State Space Model for Efficient Video Understanding
Paper • 2403.06977 • Published • 21 -
Gemma: Open Models Based on Gemini Research and Technology
Paper • 2403.08295 • Published • 41 -
On the Societal Impact of Open Foundation Models
Paper • 2403.07918 • Published • 16 -
Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models
Paper • 2403.16999 • Published • 3 -
Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos
Paper • 2403.13044 • Published • 13 -
InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding
Paper • 2403.15377 • Published • 16 -
AnyV2V: A Plug-and-Play Framework For Any Video-to-Video Editing Tasks
Paper • 2403.14468 • Published • 18 -
Long-form factuality in large language models
Paper • 2403.18802 • Published • 23 -
Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM
Paper • 2403.07487 • Published • 11 -
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Paper • 2403.05530 • Published • 49 -
Gecko: Versatile Text Embeddings Distilled from Large Language Models
Paper • 2403.20327 • Published • 41 -
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Paper • 2404.02258 • Published • 99 -
ReALM: Reference Resolution As Language Modeling
Paper • 2403.20329 • Published • 20 -
SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing
Paper • 2404.05717 • Published • 23 -
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Paper • 2404.04125 • Published • 25 -
ReFT: Representation Finetuning for Language Models
Paper • 2404.03592 • Published • 70 -
RULER: What's the Real Context Size of Your Long-Context Language Models?
Paper • 2404.06654 • Published • 30 -
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 79 -
CodecLM: Aligning Language Models with Tailored Synthetic Data
Paper • 2404.05875 • Published • 15 -
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 61 -
Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models
Paper • 2404.12387 • Published • 34 -
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Paper • 2404.10667 • Published • 11 -
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Paper • 2404.12253 • Published • 49 -
Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video
Paper • 2404.09833 • Published • 27 -
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
Paper • 2404.09990 • Published • 11 -
Many-Shot In-Context Learning
Paper • 2404.11018 • Published • 2 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 228 -
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework
Paper • 2404.14619 • Published • 118 -
Make Your LLM Fully Utilize the Context
Paper • 2404.16811 • Published • 48 -
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Paper • 2404.16873 • Published • 22 -
Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models
Paper • 2404.18796 • Published • 60 -
Extending Llama-3's Context Ten-Fold Overnight
Paper • 2404.19553 • Published • 24 -
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
Paper • 2405.01535 • Published • 71 -
FLAME: Factuality-Aware Alignment for Large Language Models
Paper • 2405.01525 • Published • 16 -
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Paper • 2310.17884 • Published • 1 -
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
Paper • 2310.08584 • Published • 2