Yang Wj's picture

1 5

Yang Wj

yangwj211

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling

upvoted a paper 4 months ago

F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data

upvoted a paper 8 months ago

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions

View all activity

Organizations

None yet

New activity in perplexity-ai/r1-1776 11 months ago

This model performs worse in complex problems compared to the DeepSeek R1

#254 opened 11 months ago by

New activity in failspy/InternVL-Chat-V1-5-4bit over 1 year ago

RuntimeError: shape mismatch: value tensor of shape [64, 6144] cannot be broadcast to indexing result of shape [256, 6144]

#2 opened over 1 year ago by