Heming Xia
@hemingkx
Followers
1K
Following
317
Statuses
107
Ph.D. student @HongKongPolyU | Prev MEng & BSc @PKU1898 | Prev Intern @MSFTResearch (MSRA) | NLP | Language Modeling
Hong Kong
Joined July 2020
Is your LLM inference fast enough🧐? Welcome to our #COLING2025 tutorial "Speculative Decoding for Efficient LLM Inference" with Yongqi Li, Qian Liu @sivil_taram, Cunxiao Du, and Wenjie Li Jan 19: 9:00-12:30 (GST) Loc: Capital Suite 7 Website:
2
35
119
RT @xiangyue96: Demystifying Long CoT Reasoning in LLMs Reasoning models like R1 / O1 / O3 have gained massive atte…
0
192
0
RT @liangchen5518: Excited to introduce R1-V! We use RL with verifiable rewards to incentivize VLMs to learn general counting abilities.…
0
546
0
RT @Alibaba_Qwen: 🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vi…
0
555
0
RT @YiCheng77783310: 🎉 Check out our new paper at Microsoft! 🌟 Introducing DiffQKV, an optimized attention mechanism. Largely improve infe…
0
2
0
RT @sivil_taram: Thrilled to share that RegMix has been accepted by #ICLR2025! 🎉 Massive shoutout to the incredible co-authors @xszheng2020…
0
13
0
RT @deepseek_ai: 🚀 DeepSeek-R1 is here! ⚡ Performance on par with OpenAI-o1 📖 Fully open-source model & technical report 🏆 MIT licensed: D…
0
8K
0
Slides and video recordings will be released after the tutorial😀!
0
0
6
Check out Liang&Zekun's awesome survey on "Next Token Prediction Towards Multimodal Intelligence"!👏🔥
Proud to introduce our latest work “Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey” as our new year gift for the multimodal learning community! Paper: Github:
0
1
6
RT @deepseek_ai: 🚀 Introducing DeepSeek-V3! Biggest leap forward yet: ⚡ 60 tokens/second (3x faster than V2!) 💪 Enhanced capabilities 🛠 AP…
0
2K
0
RT @sunjiao123sun_: Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the bes…
0
905
0
Quite interesting work exploring continuous chain-of-thought👏！
Is human language the most effective space for LLMs to reason? 🤔 Introducing Coconut 🥥 (Chain of Continuous Thought): our exploration toward LLM 𝐥𝐚𝐭𝐞𝐧𝐭 reasoning. - Encodes multiple reasoning paths simultaneously🌐 - Shows advantages in planning-intense tasks 🚀
0
1
2
RT @_TobiasLee: 📢 Introducing VL-RewardBench - A new benchmark for vision-language generative reward models (VL-GenRMs)! 📊Even SOTA models…
0
26
0