Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
Paper ā¢ 2402.10110 ā¢ Published ā¢ 3
AI & ML interests
Efficient and adaptive foundation models across language and multimodal intelligence.
Recent Activity
View all activity
Papers
Demystifying When Pruning Works via Representation Hierarchies
Making Large Language Models Efficient Dense Retrievers
shwai-heĀ
authored 11
papers 26 days ago
What Matters in Transformers? Not All Attention is Needed
Paper ā¢ 2406.15786 ā¢ Published ā¢ 33
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
Paper ā¢ 2503.05066 ā¢ Published ā¢ 4
SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
Paper ā¢ 2504.10369 ā¢ Published ā¢ 2
CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
Paper ā¢ 2506.03543 ā¢ Published ā¢ 1
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs
Paper ā¢ 2505.13778 ā¢ Published ā¢ 5
Dense Video Understanding with Gated Residual Tokenization
Paper ā¢ 2509.14199 ā¢ Published ā¢ 3
Understanding and Harnessing Sparsity in Unified Multimodal Models
Paper ā¢ 2512.02351 ā¢ Published ā¢ 4
Making Large Language Models Efficient Dense Retrievers
Paper ā¢ 2512.20612 ā¢ Published ā¢ 4
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Paper ā¢ 2603.22281 ā¢ Published ā¢ 18
Demystifying When Pruning Works via Representation Hierarchies
Paper ā¢ 2603.24652 ā¢ Published ā¢ 20
shwai-heĀ
updated a
Space 26 days ago
shwai-heĀ
updated a
collection 27 days ago
shwai-heĀ
published a
Space 27 days ago
s1ghhhĀ
updated a
collection 27 days ago
shwai-heĀ
published 2
models 29 days ago
shwai-heĀ
updated a
model 29 days ago