Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
Paper
•
2405.20541
•
Published
•
4
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Organizations
None yet
Tommy930's activity
upvoted
a
paper
about 9 hours ago
upvoted
5
papers
about 10 hours ago
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Paper
•
2405.21060
•
Published
•
16
4-bit Shampoo for Memory-Efficient Network Training
Paper
•
2405.18144
•
Published
•
3
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
Paper
•
2405.20674
•
Published
•
6
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Paper
•
2405.21048
•
Published
•
7
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Paper
•
2405.21075
•
Published
•
9
upvoted
6
papers
1 day ago
Naturalistic Music Decoding from EEG Data via Latent Diffusion Models
Paper
•
2405.09062
•
Published
•
7
Dynamic data sampler for cross-language transfer learning in large language models
Paper
•
2405.10626
•
Published
•
4
Grounded 3D-LLM with Referent Tokens
Paper
•
2405.10370
•
Published
•
8
Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation
Paper
•
2405.14598
•
Published
•
11
Thermodynamic Natural Gradient Descent
Paper
•
2405.13817
•
Published
•
13
ReVideo: Remake a Video with Motion and Content Control
Paper
•
2405.13865
•
Published
•
21
upvoted
4
papers
2 days ago
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
Paper
•
2405.19707
•
Published
•
1
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
Paper
•
2405.19856
•
Published
•
4
Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
Paper
•
2405.19888
•
Published
•
2
MotionLLM: Understanding Human Behaviors from Human Motions and Videos
Paper
•
2405.20340
•
Published
•
14
upvoted
7
papers
3 days ago
PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting
Paper
•
2405.19957
•
Published
•
4
Xwin-LM: Strong and Scalable Alignment Practice for LLMs
Paper
•
2405.20335
•
Published
•
13
MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model
Paper
•
2405.20222
•
Published
•
9
GECO: Generative Image-to-3D within a SECOnd
Paper
•
2405.20327
•
Published
•
5
DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation
Paper
•
2405.20289
•
Published
•
6
Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
Paper
•
2405.19893
•
Published
•
17
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
Paper
•
2405.20204
•
Published
•
21
upvoted
13
papers
4 days ago
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
Paper
•
2405.18991
•
Published
•
11
Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
Paper
•
2405.18515
•
Published
•
3
SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Paper
•
2405.18503
•
Published
•
5
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Paper
•
2405.19107
•
Published
•
8
Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF
Paper
•
2405.19320
•
Published
•
6
Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities
Paper
•
2405.18669
•
Published
•
9
NPGA: Neural Parametric Gaussian Avatars
Paper
•
2405.19331
•
Published
•
6
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
Paper
•
2405.19332
•
Published
•
10
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
Paper
•
2405.19325
•
Published
•
10
LLMs achieve adult human performance on higher-order theory of mind tasks
Paper
•
2405.18870
•
Published
•
13
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
Paper
•
2405.18750
•
Published
•
16
MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
Paper
•
2405.19327
•
Published
•
40
3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
Paper
•
2405.18424
•
Published
•
7
upvoted
7
papers
5 days ago
Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning
Paper
•
2405.18386
•
Published
•
13
GFlow: Recovering 4D World from Monocular Video
Paper
•
2405.18426
•
Published
•
13
Yuan 2.0-M32: Mixture of Experts with Attention Router
Paper
•
2405.17976
•
Published
•
16
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
Paper
•
2405.17991
•
Published
•
9
2BP: 2-Stage Backpropagation
Paper
•
2405.18047
•
Published
•
20
LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models
Paper
•
2405.18377
•
Published
•
12
Phased Consistency Model
Paper
•
2405.18407
•
Published
•
36
upvoted
15
papers
6 days ago
LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters
Paper
•
2405.16287
•
Published
•
9
I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models
Paper
•
2405.16537
•
Published
•
15
Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
Paper
•
2405.17414
•
Published
•
7
Human4DiT: Free-view Human Video Generation with 4D Diffusion Transformer
Paper
•
2405.17405
•
Published
•
13
Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models
Paper
•
2405.16759
•
Published
•
7
EM Distillation for One-step Diffusion Models
Paper
•
2405.16852
•
Published
•
10
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
Paper
•
2405.17428
•
Published
•
13
Transformers Can Do Arithmetic with the Right Embeddings
Paper
•
2405.17399
•
Published
•
47
Part123: Part-aware 3D Reconstruction from a Single-view Image
Paper
•
2405.16888
•
Published
•
10
Zamba: A Compact 7B SSM Hybrid Model
Paper
•
2405.16712
•
Published
•
17
Looking Backward: Streaming Video-to-Video Translation with Feature Banks
Paper
•
2405.15757
•
Published
•
12
Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
Paper
•
2405.16822
•
Published
•
11
Trans-LoRA: towards data-free Transferable Parameter Efficient Finetuning
Paper
•
2405.17258
•
Published
•
11
An Introduction to Vision-Language Modeling
Paper
•
2405.17247
•
Published
•
67
Matryoshka Multimodal Models
Paper
•
2405.17430
•
Published
•
29
upvoted
2
papers
7 days ago