Lightnews — Scholar-powered news

Reposted by Seong Joon Oh

Parameter Lab @parameterlab.bsky.social · Aug 21

🫗 An LLM's "private" reasoning may leak your sensitive data!

🎉 Excited to share our paper "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" was accepted at #EMNLP main!

1/2

Overall diagram about contextual privacy & LRMs

1 1 4

Reposted by Seong Joon Oh

Parameter Lab @parameterlab.bsky.social · Jun 23

🔎Does Conversational SEO actually work? Our new benchmark has an answer!
Excited to announce our new paper: C-SEO Bench: Does Conversational SEO Work?

🌐 RTAI: researchtrend.ai/papers/2506....
📄 Paper: arxiv.org/abs/2506.11097
💻 Code: github.com/parameterlab...
📊 Data: huggingface.co/datasets/par...

1 1 2

Reposted by Seong Joon Oh

ResearchTrend.AI Daily @researchtrend.ai · Mar 24

📅 March 28th is an exciting day for scientific networking! 🚀

Join our Connect sessions on VLM, FedML, and LLMAG—top researchers will present their latest findings!
🔗 Zoom Link: us06web.zoom.us/j/8409727334...

#ResearchTrend #AI #Networking #VLM #FedML #LLMAG

1 2

Seong Joon Oh @coallaoh.bsky.social · Feb 14

ResearchTrend.AI is hiring a data engineer - python, airflow, and postgre talents ate required (+experience with LLMs would be awesome). Please apply to [email protected] or dm me!!!

Parameter Lab @parameterlab.bsky.social · Feb 14

👥 We're Hiring: Senior/Junior Data Engineer!

📍 Remote or Local | Full-Time or Part-Time

At ResearchTrend.AI, we’re building a platform that connects researchers and AI engineers worldwide—helping them stay ahead with daily digests, insightful summaries, and interactive events.

ResearchTrend.AI

Explore the most trending research topics in AI

ResearchTrend.AI

4

Seong Joon Oh @coallaoh.bsky.social · Feb 13

Today's featured community is a unique one: Optimal Transport. It sits at the intersection of several machine learning subfields.

Follow the community to receive updates: researchtrend.ai/communities/OT

4

Seong Joon Oh @coallaoh.bsky.social · Feb 11

Audio LLM community is now available on ResearchTrend.AI!
researchtrend.ai/communities/...

Check out our cool video :)

ResearchTrend.AI Daily @researchtrend.ai · Feb 11

Introducing our Audio LLM community!

Latest papers: researchtrend.ai/communities/...

Since 2020, research has surged, proving the field’s rapid growth and potential for groundbreaking applications.

Want more research communities on ResearchTrend.AI? Drop suggestions! 👇😊

1 4

Seong Joon Oh @coallaoh.bsky.social · Feb 7

AI in education has gained significant momentum since the beginning of the "LLM era" (2023).

Check out the papers at researchtrend.ai/communities/....

2

Reposted by Seong Joon Oh

ResearchTrend.AI Daily @researchtrend.ai · Feb 3

🚀 We launched the Graph Neural Networks (GNN) community on ResearchTrend.AI!

Explore papers: researchtrend.ai/communities/...

GNNs extend neural networks to graph data. The field boomed (2017-2020), plateaued (2020-21), and is now declining.
Is this success, hype, or limits? 🤔 Share your thoughts!

2 2

Seong Joon Oh @coallaoh.bsky.social · Jan 23

Paper: arxiv.org/abs/2409.16797

Code: github.com/AlexanderRub...

OpenReview: openreview.net/forum?id=BQE...

Scalable Ensemble Diversification for OOD Generalization and Detection

Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detecti...

arxiv.org

4

Seong Joon Oh @coallaoh.bsky.social · Jan 23

Thank Alex for his great efforts and work ethic. Thank @damienteney.bsky.social and @lucascimeca.bsky.social for their continued help with this paper. We’ll humbly address the criticisms to improve it further for future opportunities.

1 1 5

Seong Joon Oh @coallaoh.bsky.social · Jan 23

We were a bit unlucky with the reviewers - one voted for acceptance, while the other two remained silent during the discussion phase. What matters, though, is knowing this is solid work and the method works. That’s how we survive the review process.

1 3

Seong Joon Oh @coallaoh.bsky.social · Jan 23

- Outcome: Scaled ensemble diversification to ImageNet level, achieving improved OOD generalisation and detection.

1

Seong Joon Oh @coallaoh.bsky.social · Jan 23

Rejected at #ICLR2025:

Scalable Ensemble Diversification for OOD Generalisation and Detection

- Current approach: Ensemble diversification relies on a separate source of OOD samples for training models to diversify outputs.

- Ours: Use samples from the training set itself to diversify ensembles.

1 1 2

Seong Joon Oh @coallaoh.bsky.social · Jan 23

If you can't wait for the arXiv version, check out the ICLR forum: openreview.net/forum?id=ByC...

PS: This paper had 6 reviewers, unanimously voting for acceptance eventually (score 6+). Such luck is rare for me 😅 I'm glad that the hard work paid off, @auselis.bsky.social. Let's arXiv it!

This link will take you to a page that’s not on LinkedIn

lnkd.in

2

Seong Joon Oh @coallaoh.bsky.social · Jan 23

Another #ICLR2025 paper:

Intermediate Layer Classifiers for OOD generalization

- Common approach: Use penultimate-layer features of pre-trained models for downstream tasks.

- Our recommendation: Explore lower-layer features. You'll likely find better layers for OOD generalisation.

2 1 6

Seong Joon Oh @coallaoh.bsky.social · Jan 23

Thank other co-authors too: Alexander Rubinstein and Ehsan Abbasnejad.

paper: arxiv.org/abs/2403.07968
code: github.com/aktsonthalia...

Do Deep Neural Network Solutions Form a Star Domain?

It has recently been conjectured that neural network solution sets reachable via stochastic gradient descent (SGD) are convex, considering permutation invariances (Entezari et al., 2022). This means t...

arxiv.org

1

Seong Joon Oh @coallaoh.bsky.social · Jan 23

I.e., at a reasonable width (no wideresnet), solutions already form a star domain.

Side note: We developed a method for finding the "star model", a special solution connected to all other solutions. I couldn't resist naming it "NeuralStarLink" but fortunately the first author Ankit held me back :)

Do Deep Neural Network Solutions Form a Star Domain?

It has recently been conjectured that neural network solution sets reachable via stochastic gradient descent (SGD) are convex, considering permutation invariances (Entezari et al., 2022). This means t...

arxiv.org

1 2

Seong Joon Oh @coallaoh.bsky.social · Jan 23

Finally accepted! #ICLR2025

Do Deep Neural Network Solutions Form a Star Domain?

- Known: as DNN width --> infty, solutions become convex modulo permutations of neurons.

- What's new: as DNN width --> infty, solutions **first form a star domain** and then a convex domain modulo permutations.

2 2 23

Seong Joon Oh @coallaoh.bsky.social · Dec 31

✨ Coming soon: Email digests for the authors and organisations you follow. Stay tuned for more updates!

Let’s make 2025 a year of learning and staying connected! 🚀

3/3

3

Seong Joon Oh @coallaoh.bsky.social · Dec 31

📩 How to get started:

- New users: Sign up here: researchtrend.ai/auth/signup and select “I agree to receive personalised daily email digests featuring the latest arXiv papers.”

- Existing users: Update your preferences in your profile: researchtrend.ai/profile.

2/3

Sign Up | ResearchTrend.AI

Explore the most trending research topics in AI

researchtrend.ai

1 2

Seong Joon Oh @coallaoh.bsky.social · Dec 31

🎉 Happy New Year!

We’re excited to announce the launch of our email digest feature on ResearchTrend.AI! 🚀

You can now receive daily updates from the research communities you follow. Stay informed!

1/3

1 1 3

Reposted by Seong Joon Oh

Serge Belongie @serge.belongie.com · Dec 29

Here’s a podcast I did with Danish journalist Lone Frank during Folkemødet on Bornholm last summer. The opening blurb is in Danish, and the rest is in English. We talk about my move from the US to DK, and the Pioneer Centre for AI’s unique approach to research.

Carlsbergfondet @carlsbergfondet.dk · Dec 29

🎙️Hvordan sikrer vi, at AI skaber positive fremskridt til gavn for mennesker og samfund verden over? Hør eller genhør podcast med AI-ekspert @serge.belongie.com & Lone Frank. Liveoptagelse fra årets #fmdk👉 bit.ly/4dXsjZ8 #dkforsk @aicentre.dk

2 18

Seong Joon Oh @coallaoh.bsky.social · Dec 29

💡 Follow these fast-evolving domains and join their discussions on researchtrend.ai ! 🚀 5/5

ResearchTrend.AI

Explore the most trending research topics in AI

researchtrend.ai

2

Seong Joon Oh @coallaoh.bsky.social · Dec 29

📊 Language Models for Tabular Data (LMTD)
While deep learning has conquered vision and language, tabular data remains a challenge. Let's see what happens in 2025. LMTD is gaining traction as researchers push the boundaries to unlock its full potential.
researchtrend.ai/communities/... 4/5

Language Models for Tabular Data (LMTD)

Leverage the power of large language models to process diverse tables and perform various tabular tasks based on natural language instructions.

researchtrend.ai

1 2

Seong Joon Oh @coallaoh.bsky.social · Dec 29

🤖 Large-Language Model Agents (LLMAG)
2025 is shaping up to be a transformative year for LLM agents. The surge in interest reflects their growing role in automation, reasoning, and decision-making across domains.
researchtrend.ai/communities/... 3/5

Large-Language Model Agents (LLMAG)

LLM agents use LLMs as the main controller to execute complex tasks, integrating modules like planning, memory, and tool usage.

researchtrend.ai

1 1