Hongning Wang

Computer Science, Photography, Soccer, IT

[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: https://t.co/opFqeRvLsx

#ClaudeCode #AIEngineering #Agents #MCP #AIAgents

[Hongning Wang @feifeiM]

@guidozuc @SIGIRConf Wonderful work and look forward to an exciting SIRIG conference!

[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 @feifeiM]

(1/2) Will humans be replaced by generative AI #Sora #chatgpt4? Our recent work provides some cues from a game theoretical perspective: https://t.co/3S9bH2XKFB

[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 @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: https://t.co/39aH2UhrXg
repo: https://t.co/PkN0JfmaZ0

[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: https://t.co/39aH2UhrXg
repo: https://t.co/PkN0JfmaZ0

[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 https://t.co/aPwAiS1i0X . 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!

[Hongning Wang @feifeiM]

Want to use generalized linear bandits in a federated learning setting? Come to our #NeurIPS2022 poster #939 at 11am CST and check out our paper: https://t.co/jci8ZgdKWj to find out more details!

[Hongning Wang @feifeiM]

Finally arrived at #NeurIPS2022! Amazing location and crowd! Excited about the next three days!

[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 :)

[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 https://t.co/eR9s5NZGnP

[Hongning Wang @feifeiM]

@wang_huazheng is presenting our private bandit work: https://t.co/8VjfstuTih, at #recsys2022!

[Hongning Wang @feifeiM]

Great to see many rooms are fully packed at #KDD2022!

[Hongning Wang @feifeiM]

Going to talk about our effort in "Learning from a Learning User" at the #KDD2022 Online And Adaptive Recommender Systems workshop: https://t.co/qNBNLSPnLE. The room is fully packed!

[Hongning Wang @feifeiM]

Heading to #KDD2022 in such a beautiful afternoon!

[Hongning Wang @feifeiM]

We have a wonderful lineup of 14 full-day and 20 half-day workshops at KDD2022: https://t.co/6qOoWPUGGz, starting from this Sunday morning eastern time. Look forward to meeting everyone at the workshops and the conference!

[Hongning Wang @feifeiM]

Some contextual bandit instances are intrinsically hard to attack?! Come to our #ICML2022 talk at 4:40pm, Room 301-303. And here is our paper: https://t.co/PwZ7UPKQtm

[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: https://t.co/oBp1DrjYnd