Hanlin Wang
@hanlinwang1024
Followers
131
Following
216
Statuses
48
Polyu cs PhD student Interested in NLP | Embodied AI
Guangzhou
Joined March 2021
RT @YiCheng77783310: 🚀 Accepted by ICLR’25! We introduce Integrative Decoding, a novel decoding algorithm to tackle the hallucination prob…
0
13
0
0
4
0
RT @hemingkx: Is your LLM inference fast enough🧐? Welcome to our #COLING2025 tutorial "Speculative Decoding for Efficient LLM Inference"…
0
35
0
🌟 Welcome to check our paper accepted by International Journal of Machine Learning and Cybernetics
1
0
1
🌟 Excited to share our #EMNLP2024Findings work: E2CL: Exploration-based Error Correction Learning for Embodied Agents, a novel framework for improving embodied agents' alignment with environments! 🌟 📄 Welcome to check our work:
0
3
9
RT @ManlingLi_: 🛠️ Particularly, the evaluation also runs on BEHAVIOR (@drfeifei @jiajunwu , which is the first to…
0
3
0
RT @hemingkx: 🤔How much potential do LLMs have for self-acceleration through layer sparsity? 🚀 🚨 Excited to share our latest work: SWIFT:…
0
6
0
RT @agarwl_: I gave my first guest lecture today in a grad course on LLMs as an (soon-to-be) adjunct prof at McGill. Putting the slides her…
0
118
0
RT @wzq016: The new OpenAI o1 model is impressive! The blog says that o1 is trained to learn to refine by RL, which reminds me of my ICLR…
0
17
0
RT @rogerliuty: New survey: Towards a unified view of preference learning for LLMs! 🧠 LLMs are powerful, but aligning them with human pref…
0
19
0
RT @mattshumer_: I'm excited to announce Reflection 70B, the world’s top open-source model. Trained using Reflection-Tuning, a technique d…
0
1K
0
RT @rm_rafailov: Super excited to announce what we have been working on in the last six months - Agent Q is out now! This is a framework fo…
0
105
0
RT @JessieW35212256: Excited to #ACL2024 in Bangkok from Aug 11th-14th!🇹🇭 Come to Findings Poster Session 3 on August 13 at 12:15PM-13:15PM…
0
2
0
RT @karpathy: # RLHF is just barely RL Reinforcement Learning from Human Feedback (RLHF) is the third (and last) major stage of training a…
0
1K
0