ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Paper
•
2502.00299
•
Published
•
2
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted
a
paper
3 days ago
Scalable-Softmax Is Superior for Attention
upvoted
a
paper
3 days ago
Almost Surely Safe Alignment of Large Language Models at Inference-Time
Organizations
None yet
Tommy930's activity
upvoted
7
papers
3 days ago
Scalable-Softmax Is Superior for Attention
Paper
•
2501.19399
•
Published
•
20
Almost Surely Safe Alignment of Large Language Models at Inference-Time
Paper
•
2502.01208
•
Published
•
11
MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation
Paper
•
2502.01572
•
Published
•
20
SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
Paper
•
2502.01639
•
Published
•
24
Activation-Informed Merging of Large Language Models
Paper
•
2502.02421
•
Published
•
3
Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression
Paper
•
2502.04296
•
Published
•
6
upvoted
7
papers
4 days ago
Weak-to-Strong Diffusion with Reflection
Paper
•
2502.00473
•
Published
•
19
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Paper
•
2502.04320
•
Published
•
30
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
Paper
•
2502.03032
•
Published
•
53
ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution
Paper
•
2502.00989
•
Published
•
7
MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation
Paper
•
2502.04299
•
Published
•
14
PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback
Paper
•
2502.00988
•
Published
•
5
Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment
Paper
•
2502.04328
•
Published
•
19
upvoted
6
papers
5 days ago
PILAF: Optimal Human Preference Sampling for Reward Modeling
Paper
•
2502.04270
•
Published
•
10
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper
•
2502.04128
•
Published
•
19
Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
Paper
•
2502.04295
•
Published
•
8
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
Paper
•
2502.03860
•
Published
•
18
UltraIF: Advancing Instruction Following from the Wild
Paper
•
2502.04153
•
Published
•
20
ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
Paper
•
2502.04306
•
Published
•
16