Self-Alignment with Instruction Backtranslation
Paper • 2308.06259 • Published • 43
My Papers of Interest
-
-
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
Paper • 2308.03793 • Published • 12 -
From Sparse to Soft Mixtures of Experts
Paper • 2308.00951 • Published • 22 -
Revisiting DETR Pre-training for Object Detection
Paper • 2308.01300 • Published • 10 -
Unified Model for Image, Video, Audio and Language Tasks
Paper • 2307.16184 • Published • 16 -
Scaling TransNormer to 175 Billion Parameters
Paper • 2307.14995 • Published • 23 -
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
Paper • 2307.14620 • Published • 15 -
Less is More: Focus Attention for Efficient DETR
Paper • 2307.12612 • Published • 7 -
Replacing softmax with ReLU in Vision Transformers
Paper • 2309.08586 • Published • 19 -
A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale
Paper • 2309.06497 • Published • 7 -
Multimodal Foundation Models: From Specialists to General-Purpose Assistants
Paper • 2309.10020 • Published • 41 -
FoleyGen: Visually-Guided Audio Generation
Paper • 2309.10537 • Published • 8 -
LMDX: Language Model-based Document Information Extraction and Localization
Paper • 2309.10952 • Published • 67 -
RMT: Retentive Networks Meet Vision Transformers
Paper • 2309.11523 • Published • 34 -
Aligning Large Multimodal Models with Factually Augmented RLHF
Paper • 2309.14525 • Published • 32 -
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Paper • 2309.15098 • Published • 7 -
Vision Transformers Need Registers
Paper • 2309.16588 • Published • 86 -
AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models
Paper • 2309.16414 • Published • 18 -
Enable Language Models to Implicitly Learn Self-Improvement From Data
Paper • 2310.00898 • Published • 24 -
Lemur: Harmonizing Natural Language and Code for Language Agents
Paper • 2310.06830 • Published • 33 -
PaLI-3 Vision Language Models: Smaller, Faster, Stronger
Paper • 2310.09199 • Published • 28 -
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Paper • 2310.09478 • Published • 21 -
Context-Aware Meta-Learning
Paper • 2310.10971 • Published • 17 -
An Early Evaluation of GPT-4V(ision)
Paper • 2310.16534 • Published • 22 -
Segment and Caption Anything
Paper • 2312.00869 • Published • 20 -
OneLLM: One Framework to Align All Modalities with Language
Paper • 2312.03700 • Published • 24 -
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
Paper • 2505.14810 • Published • 62 -
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning
Paper • 2505.15966 • Published • 53