Chaeeun Kim (@chaechaek1214) - Twitter Profili | Zamantika Mersobahis Locabet

Sabitlenmiş Tweet

Chaeeun Kim@chaechaek1214·24 May

❓What if your RAG didn’t need a separate retrieval model at all? We present 🧊FREESON, a new framework for retriever-FREE retrieval-augmented reasoning. With FREESON, a single LRM acts as both generator and retriever, shifting the focus from seq2seq matching to locating answer-containing regions within corpora for retrieval. ✅ Lower retrieval overhead ✅ Direct, precise access to relevant information

English

1

5

30

6.2K

Chaeeun Kim@chaechaek1214·4 Kas

I'm at #EMNLP2025 this week in Suzhou to present LegalSearchLM! 🤗 Wed, 16:30-18:00 📄paper: arxiv.org/abs/2505.23832 Come see how we - use first-token-aware autoregressive LMs as retrievers with an FM-index for legal-element reasoning in complex legal case retrieval - release the largest Korean legal case retrieval benchmark — 411 crime types & 1.2M+ cases, plus a hard subset with case-specific legal facts & issues #NLLP2025 #LegalNLP

English

0

3

18

2.2K

Chaeeun Kim retweetledi

The Humanoid Hub@TheHumanoidHub·16 Tem

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

English

10

38

217

21K

Chaeeun Kim retweetledi

Seungone Kim@seungonekim·24 May

Within the RAG pipeline, the retriever often acts as the bottleneck! Instead of training a better embedding model, we explore using a reasoning model both as the retriever&generator. To do this, we add MCTS to the generative retrieval pipeline. Check out @chaechaek1214's post!

Chaeeun Kim@chaechaek1214

❓What if your RAG didn’t need a separate retrieval model at all? We present 🧊FREESON, a new framework for retriever-FREE retrieval-augmented reasoning. With FREESON, a single LRM acts as both generator and retriever, shifting the focus from seq2seq matching to locating answer-containing regions within corpora for retrieval. ✅ Lower retrieval overhead ✅ Direct, precise access to relevant information

English

0

1

31

2.8K

Chaeeun Kim@chaechaek1214·24 May

Huge thanks to my co-author @seungonekim. Your feedback and discussions were really helpful, and I truly enjoyed working together😊

English

0

2

475

Chaeeun Kim@chaechaek1214·24 May

Please check out our paper: arxiv.org/abs/2505.16409 Code release is coming soon, stay tuned!

English

1

0

2

458

Chaeeun Kim@chaechaek1214·24 May

❓What if your RAG didn’t need a separate retrieval model at all? We present 🧊FREESON, a new framework for retriever-FREE retrieval-augmented reasoning. With FREESON, a single LRM acts as both generator and retriever, shifting the focus from seq2seq matching to locating answer-containing regions within corpora for retrieval. ✅ Lower retrieval overhead ✅ Direct, precise access to relevant information

English

1

5

30

6.2K

Chaeeun Kim retweetledi

Dongkeun Yoon@dongkeun_yoon·21 May

🙁 LLMs are overconfident even when they are dead wrong. 🧐 What about reasoning models? Can they actually tell us “My answer is only 60% likely to be correct”? ❗Our paper suggests that they can! Through extensive analysis, we investigate what enables this emergent ability.

English

9

47

301

34.8K

Chaeeun Kim retweetledi

Seungone Kim@seungonekim·25 Nis

🏆Glad to share that our BiGGen Bench paper has received the best paper award at @naaclmeeting! x.com/naaclmeeting/s… 📅 Ballroom A, Session I: Thursday May 1st, 16:00-17:30 (MDT) 📅 Session M (Plenary Session): Friday May 2nd, 15:30-16:30 (MDT) 📅 Virtual Conference: Tuesday May 6th, 20:30-21:00 (MDT) I'd like to appreciate our coauthors @scott_sjy Ji Yong Cho @ShayneRedford @chaechaek1214 @dongkeun_yoon @gson_AI Yejin Cho @shafayat_sheikh @jinheonbaek @suehpark @ronalhwang @Jinkyung_Jo Hyowon Cho @haebinshin_ @sylee_ai @hanseok_oh @nlee288 @itsnamgyu @joocjun @miyoung_ko @yoonjoo_le2 @hyungjoochae @jay_shin @jang_yoel @SeonghyeonYe @billyuchenlin @wellecks @gneubig Moontae Lee @Kyungjae__Lee @seo_minjoon! It wouldn't have been possible without everyone's feedback and hard work 😀

Seungone Kim@seungonekim

🤔How can we systematically assess an LM's proficiency in a specific capability without using summary measures like helpfulness or simple proxy tasks like multiple-choice QA? Introducing the ✨BiGGen Bench, a benchmark that directly evaluates nine core capabilities of LMs.

English

10

21

131

31.7K

Chaeeun Kim@chaechaek1214·17 Mar

@jang_yoel @NVIDIAAI Congratulations Joel!!

English

0

2

192

Joel Jang@jang_yoel·17 Mar

Some personal life update: I have joined @NVIDIAAI GEAR lab as a full-time Research Scientist last month (after one year as a research intern)! I’ll continue to be working on developing general-purpose robot foundation models. Stay tuned for some exciting updates!

English

29

2

349

25.3K

Chaeeun Kim retweetledi

Jinu Lee@jinulee_v·24 Şub

📢 Interested in evaluating the quality of CoT reasoning steps, but don't know where to start? Here is a new survey for you! arxiv.org/abs/2502.12289 (1/3)

English

2

20

114

13.4K

Chaeeun Kim

Keşfet