PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models
Paper
•
2402.08714
•
Published
•
11
Papers to read
-
-
Data Engineering for Scaling Language Models to 128K Context
Paper • 2402.10171 • Published • 22 -
RLVF: Learning from Verbal Feedback without Overgeneralization
Paper • 2402.10893 • Published • 10 -
Coercing LLMs to do and reveal (almost) anything
Paper • 2402.14020 • Published • 12 -
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
Paper • 2402.14658 • Published • 82 -
TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Paper • 2402.14289 • Published • 19 -
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 112 -
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Paper • 2402.16822 • Published • 15 -
Beyond Language Models: Byte Models are Digital World Simulators
Paper • 2402.19155 • Published • 49 -
Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
Paper • 2403.02677 • Published • 16 -
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Paper • 2402.11753 • Published • 5 -
How Far Are We from Intelligent Visual Deductive Reasoning?
Paper • 2403.04732 • Published • 18 -
Evaluating and Mitigating Discrimination in Language Model Decisions
Paper • 2312.03689 • Published • 1 -
How predictable is language model benchmark performance?
Paper • 2401.04757 • Published • 2 -
PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
Paper • 2305.02547 • Published • 7 -
Is Cosine-Similarity of Embeddings Really About Similarity?
Paper • 2403.05440 • Published • 3 -
Multistep Consistency Models
Paper • 2403.06807 • Published • 14 -
LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History
Paper • 2402.18216 • Published • 1 -
V3D: Video Diffusion Models are Effective 3D Generators
Paper • 2403.06738 • Published • 28 -
Mixtral of Experts
Paper • 2401.04088 • Published • 159 -
RAFT: Adapting Language Model to Domain Specific RAG
Paper • 2403.10131 • Published • 67 -
Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation
Paper • 2403.16990 • Published • 25 -
Can large language models explore in-context?
Paper • 2403.15371 • Published • 32 -
DreamLIP: Language-Image Pre-training with Long Captions
Paper • 2403.17007 • Published • 1 -
Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models
Paper • 2403.20331 • Published • 14 -
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
Paper • 2404.01331 • Published • 25 -
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 64 -
Stream of Search (SoS): Learning to Search in Language
Paper • 2404.03683 • Published • 25 -
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
Paper • 2404.05726 • Published • 20 -
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
Paper • 2404.07143 • Published • 103 -
Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations
Paper • 2404.07153 • Published • 1 -
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback
Paper • 2404.07987 • Published • 47 -
Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models
Paper • 2404.07973 • Published • 30 -
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model
Paper • 2404.09967 • Published • 20 -
MeshLRM: Large Reconstruction Model for High-Quality Mesh
Paper • 2404.12385 • Published • 26 -
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
Paper • 2404.12803 • Published • 29 -
Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
Paper • 2404.13013 • Published • 30 -
SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
Paper • 2404.14396 • Published • 18 -
How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study
Paper • 2404.14047 • Published • 44 -
Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
Paper • 2404.14507 • Published • 21 -
InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation
Paper • 2404.19427 • Published • 71 -
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report
Paper • 2405.00732 • Published • 118 -
Corrective Retrieval Augmented Generation
Paper • 2401.15884 • Published • 3 -
Observational Scaling Laws and the Predictability of Language Model Performance
Paper • 2405.10938 • Published • 11 -
Your Transformer is Secretly Linear
Paper • 2405.12250 • Published • 150 -
Diffusion for World Modeling: Visual Details Matter in Atari
Paper • 2405.12399 • Published • 27 -
LANISTR: Multimodal Learning from Structured and Unstructured Data
Paper • 2305.16556 • Published • 2 -
Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
Paper • 2405.11273 • Published • 17 -
Not All Language Model Features Are Linear
Paper • 2405.14860 • Published • 39 -
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
Paper • 2405.15319 • Published • 25 -
Phased Consistency Model
Paper • 2405.18407 • Published • 46 -
MotionLLM: Understanding Human Behaviors from Human Motions and Videos
Paper • 2405.20340 • Published • 19 -
Xwin-LM: Strong and Scalable Alignment Practice for LLMs
Paper • 2405.20335 • Published • 17 -
LLMs achieve adult human performance on higher-order theory of mind tasks
Paper • 2405.18870 • Published • 17 -
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback
Paper • 2406.00888 • Published • 30 -
Guiding a Diffusion Model with a Bad Version of Itself
Paper • 2406.02507 • Published • 15 -
Self-Improving Robust Preference Optimization
Paper • 2406.01660 • Published • 18 -
PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM
Paper • 2406.02884 • Published • 15 -
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Paper • 2406.02657 • Published • 37 -
Proofread: Fixes All Errors with One Tap
Paper • 2406.04523 • Published • 12 -
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Paper • 2406.07476 • Published • 32 -
MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
Paper • 2406.08407 • Published • 24 -
Large Language Model Unlearning via Embedding-Corrupted Prompts
Paper • 2406.07933 • Published • 7 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 50 -
TextGrad: Automatic "Differentiation" via Text
Paper • 2406.07496 • Published • 27 -
Make It Count: Text-to-Image Generation with an Accurate Number of Objects
Paper • 2406.10210 • Published • 76 -
XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Paper • 2406.08973 • Published • 86 -
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Paper • 2406.11833 • Published • 61 -
mDPO: Conditional Preference Optimization for Multimodal Large Language Models
Paper • 2406.11839 • Published • 37 -
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Paper • 2406.11813 • Published • 30 -
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 65 -
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation
Paper • 2406.12849 • Published • 49 -
Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
Paper • 2406.12034 • Published • 14 -
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
Paper • 2406.10601 • Published • 65 -
A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems
Paper • 2406.14972 • Published • 7 -
EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
Paper • 2406.13457 • Published • 16 -
PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers
Paper • 2406.12430 • Published • 7 -
Weight subcloning: direct initialization of transformers using larger pretrained ones
Paper • 2312.09299 • Published • 17 -
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Paper • 2406.17419 • Published • 16 -
Large Language Models Assume People are More Rational than We Really are
Paper • 2406.17055 • Published • 4 -
DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
Paper • 2406.16855 • Published • 54 -
Video-Infinity: Distributed Long Video Generation
Paper • 2406.16260 • Published • 28 -
VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
Paper • 2406.16338 • Published • 25 -
Adam-mini: Use Fewer Learning Rates To Gain More
Paper • 2406.16793 • Published • 67 -
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Paper • 2406.19389 • Published • 51 -
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
Paper • 2406.20095 • Published • 17 -
MagMax: Leveraging Model Merging for Seamless Continual Learning
Paper • 2407.06322 • Published • 1 -
A Single Transformer for Scalable Vision-Language Modeling
Paper • 2407.06438 • Published • 1 -
Video Diffusion Alignment via Reward Gradients
Paper • 2407.08737 • Published • 47 -
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
Paper • 2407.09025 • Published • 128 -
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
Paper • 2407.09121 • Published • 5 -
GAVEL: Generating Games Via Evolution and Language Models
Paper • 2407.09388 • Published • 14 -
Map It Anywhere (MIA): Empowering Bird's Eye View Mapping using Large-scale Public Data
Paper • 2407.08726 • Published • 8 -
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
Paper • 2407.08303 • Published • 17 -
NeedleBench: Can LLMs Do Retrieval and Reasoning in 1 Million Context Window?
Paper • 2407.11963 • Published • 43 -
How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
Paper • 2402.07282 • Published • 1 -
Fewer Truncations Improve Language Modeling
Paper • 2404.10830 • Published • 3 -
One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
Paper • 2407.00256 • Published • 1 -
Provably Robust DPO: Aligning Language Models with Noisy Feedback
Paper • 2403.00409 • Published • 1 -
Efficient Exploration for LLMs
Paper • 2402.00396 • Published • 21 -
Text2SQL is Not Enough: Unifying AI and Databases with TAG
Paper • 2408.14717 • Published • 24 -
Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance
Paper • 2409.04593 • Published • 22