Office Hours 001

Like 👍. Comment 💬. Subscribe 🟥.
🏘 Discord: / discord
github.com/hu-...
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
arxiv.org/pdf/...
Compress then Serve: Serving Thousands of LoRA
Adapters with Little Overhead
www.arxiv.org/...
Scaling Synthetic Data Creation with 1,000,000,000 Personas
arxiv.org/pdf/...
µ-BENCH: VISION-LANGUAGE BENCHMARK FOR MICROSCOPY
UNDERSTANDING
arxiv.org/pdf/...
PaliGemma: A versatile 3B VLM for transfer
arxiv.org/pdf/...
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
www.together.a...
Distilling System 2 into System 1
arxiv.org/pdf/...
Inference Performance Optimization for Large Language Models on CPUs
arxiv.org/pdf/...
AgentInstruct: Toward Generative Teaching with Agentic Flows
arxiv.org/pdf/...
VIDEO-STAR: SELF-TRAINING ENABLES VIDEO INSTRUCTION TUNING WITH ANY SUPERVISION
arxiv.org/pdf/...

[@Amirmohamadshafiee]

❤❤ very good

[@andydataguy]

Ah looks like i just missed you! Glad to see you streaming 🙌🏾

[@sathishkumar-ch4sx]

This type of stream really helps, I like what you said it's about generalization. focusing on a broader and diverse set of papers. I look forward to watch your upcoming videos

[@NLPprompter]

aw crap i didn't understand anything.... i must re learn what ever hits talking... this is like a week set back for me 😭

[@Amirmohamadshafiee]

❤❤ very good