Hongning Wang

63 posts

Hongning Wang

Hongning Wang

@feifeiM

Computer Science, Photography, Soccer, IT

VA Katılım Eylül 2009
375 Takip Edilen177 Takipçiler
Hongning Wang
Hongning Wang@feifeiM·
Lifelong learning is hard, but exciting!
Chengxing Xie@Chengxing_Xie

Claude Code may be hiding far more than most people realize We analyzed a source snapshot and found evidence of 24+ gated feature systems, including: coordinator mode, forked subagents, agent swarms, Kairos, Auto Dream, and deep MCP/auth infrastructure... The real story is the 3-layer gating architecture behind it. Read: yitianlian.github.io/claude-code-hi… #ClaudeCode #AIEngineering #Agents #MCP #AIAgents

English
0
0
0
33
Guido Zuccon
Guido Zuccon@guidozuc·
In Frankfurt airpot waiting to fly to #ecir2024... and in the meantime writing a bit more code to support our analysis of #sigir2024 reviews. This year we wrote more than 1k lines of code and execute 500+ hours of computations to analyse SIGIR submissions and reviews @SIGIRConf
Guido Zuccon tweet media
English
7
2
44
3.6K
Hongning Wang
Hongning Wang@feifeiM·
(2b/2) Q: Would the rise of genAI-powered creators discourage the productivity and utility of human creators? A: The total utility and content generation by human creators decrease, but the average utility and content output per human creator actually improve!
Hongning Wang tweet media
English
0
0
1
214
Hongning Wang
Hongning Wang@feifeiM·
(2a/2) Leave alone cold theoretical results, simulations suggest several interesting phenomena which are predicted by our theorems. For example, Q: who will switch to using generative AI? A: Those with high creation cost.
Hongning Wang tweet media
English
1
0
1
325
Hongning Wang
Hongning Wang@feifeiM·
Really excited about our recent work on RLHF: from a probability matching perspective, we showed that DPO does mean-seeking, while our EXO does mode-seeking!
Haozhe Ji@HaozJi

Introducing EXO, a method towards efficient exact optimization of LM alignment. tldr: EXO is more efficient than RLHF by perfoming probability matching, and exact for arbitary policy parametrization compared to DPO. arxiv: arxiv.org/pdf/2402.00856… repo: github.com/cdjhz/exact-op…

English
0
0
4
343
Hongning Wang retweetledi
Haozhe Ji
Haozhe Ji@HaozJi·
Introducing EXO, a method towards efficient exact optimization of LM alignment. tldr: EXO is more efficient than RLHF by perfoming probability matching, and exact for arbitary policy parametrization compared to DPO. arxiv: arxiv.org/pdf/2402.00856… repo: github.com/cdjhz/exact-op…
Haozhe Ji tweet mediaHaozhe Ji tweet mediaHaozhe Ji tweet mediaHaozhe Ji tweet media
English
2
14
58
11.9K
Hongning Wang
Hongning Wang@feifeiM·
Welcome to our #ICML2023 oral presentation about a game theoretical analysis of the "invisible hands" in recommender systems! Very insightful and interesting results!
Fan Yao@FanYao55671545

#ICML2023 Excited to share our ICML oral paper arxiv.org/pdf/2302.01971… . Our result reveals the economic insight of content creator competition in recommendation platforms, which echos the insight of "invisible hand" from Adam Smith. Welcome to join our oral and poster sessions!

English
0
0
9
1.2K
Hongning Wang
Hongning Wang@feifeiM·
Finally arrived at #NeurIPS2022! Amazing location and crowd! Excited about the next three days!
Hongning Wang tweet media
English
0
0
14
0
Hongning Wang
Hongning Wang@feifeiM·
An interesting follow-up: right before my talk, the fire alarm was set off and everyone was asked to evacuate immediately. 5 minutes later, we were told it was a false alarm, which in turn brought more people to my talk :)
English
0
0
3
0
Hongning Wang
Hongning Wang@feifeiM·
Do we really need reinforcement learning for conversational recommendations? We are providing a simpler alternative using decision trees! Going to present it at #CIKM2022 tomorrow arxiv.org/pdf/2208.14614…
English
2
1
17
0
Hongning Wang
Hongning Wang@feifeiM·
Going to talk about our effort in "Learning from a Learning User" at the #KDD2022 Online And Adaptive Recommender Systems workshop: oars-workshop.github.io. The room is fully packed!
English
0
1
3
0
Hongning Wang
Hongning Wang@feifeiM·
We have a wonderful lineup of 14 full-day and 20 half-day workshops at KDD2022: kdd.org/kdd2022/worksh…, starting from this Sunday morning eastern time. Look forward to meeting everyone at the workshops and the conference!
English
0
0
3
0
Hongning Wang
Hongning Wang@feifeiM·
Wants to learn from a learning agent to improve yourself? Check out our talk this afternoon at #ICML2022, Online learning and bandit session, at ballroom 3&4! And here is the paper: arxiv.org/abs/2202.01879
English
0
0
0
0

Keşfet

@guidozuc @SIGIRConf @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates @NASA