-
Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
Paper • 2408.15998 • Published • 83 -
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Paper • 2409.01704 • Published • 80 -
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Paper • 2408.06195 • Published • 61 -
Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
Paper • 2405.06682 • Published • 2
Collections
Discover the best community collections!
Collections including paper arxiv:2410.05258
-
Associative Recurrent Memory Transformer
Paper • 2407.04841 • Published • 31 -
Mixture-of-Agents Enhances Large Language Model Capabilities
Paper • 2406.04692 • Published • 55 -
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper • 2405.21060 • Published • 63 -
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Paper • 2404.14219 • Published • 251
-
THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation
Paper • 2406.10996 • Published • 32 -
Simulating Classroom Education with LLM-Empowered Agents
Paper • 2406.19226 • Published • 29 -
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Paper • 2406.19389 • Published • 51 -
LAMBDA: A Large Model Based Data Agent
Paper • 2407.17535 • Published • 34
-
MotionLLM: Understanding Human Behaviors from Human Motions and Videos
Paper • 2405.20340 • Published • 19 -
Spectrally Pruned Gaussian Fields with Neural Compensation
Paper • 2405.00676 • Published • 8 -
Paint by Inpaint: Learning to Add Image Objects by Removing Them First
Paper • 2404.18212 • Published • 27 -
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report
Paper • 2405.00732 • Published • 118
-
Addition is All You Need for Energy-efficient Language Models
Paper • 2410.00907 • Published • 130 -
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Paper • 2402.17764 • Published • 596 -
Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding
Paper • 2404.16710 • Published • 57 -
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory
Paper • 2405.08707 • Published • 27
-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 26 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 12 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 45 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 28
-
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Paper • 2404.08801 • Published • 62 -
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models
Paper • 2404.07839 • Published • 41 -
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Paper • 2404.05892 • Published • 31 -
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Paper • 2312.00752 • Published • 138
-
Rho-1: Not All Tokens Are What You Need
Paper • 2404.07965 • Published • 84 -
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Paper • 2404.05961 • Published • 64 -
Compression Represents Intelligence Linearly
Paper • 2404.09937 • Published • 27 -
Multi-Head Mixture-of-Experts
Paper • 2404.15045 • Published • 59