Fei Liu
@feiliu_nlp
Followers
2K
Following
1K
Media
30
Statuses
89
Associate professor @EmoryUniversity. Working on large language models, LLM inference, reasoning, natural language generation, and various aspects of GenAI.
Atlanta, GA
Joined July 2018
Happy to share our paper got selected as an Oral Presentation at #ACL2025! . Out of 8,000+ submissions and 3,000+ accepted papers, only 245 were chosen for oral (<3%)!. Our amazing first author Hui Wei can't travel, so I'll be presenting in Vienna. Hope to see you there! 🇦🇹 . 📄
2
4
55
Just watched John Oliver's episode on AI Slop and loved it. He describes AI slop as the flood of low-quality, AI-generated content: music, images, short videos, maybe even news articles, books, research papers, code. you name it. Feels like we're (almost) drowning in it. Real
1
1
4
RT @XuCanwen: ❄️We're looking for a MLE/Applied Scientist to join our @Snowflake AI team to work on AI+Software Engineering. If you have sh….
0
4
0
RT @DaniYogatama: try creating reels from longer videos with reka vision: watch the video below or check out this….
0
11
0
RT @hengjinlp: I’m looking for a new postdoc to start this fall working on AI for Science/Science-Inspired AI (focusing on chemistry and bi….
0
17
0
RT @haozhangml: Pokémon Red has recently emerged as an evaluation benchmark, adopted by several top AI labs. But is it really a good bench….
0
4
0
Autonomous agents are powerful, but without guardrails, they drift into inefficiency. We view 'cost' as a form of guardrail and use Monte Carlo Tree Search with explicit cost-awareness to guide LLM-based planning. Tight cost constraints push the planner to quickly identify
Anthropic staff realized they could ask Claude to buy things that weren’t just food & drink. After someone randomly decided to ask it to order a tungsten cube, Claude ended up with an inventory full of (as it put it) “specialty metal items” that it ended up selling at a loss.
1
3
12
Just watched Nathan's recent talk and really enjoyed it. Around 19:30 is where it gets really interesting. Totally agree that planning is the exciting frontier. If you're curious, our recent survey #PlanGenLLMs is a great place to start:
Here's a recent talk I gave recapping the last 6-12 months of AI progress, why getting perfect models is hard, how labs are likely approaching the next phase of training (for agents), and other interesting tidbits across the reasoning landscape. Topics:.00:00 Introduction & the
3
9
80
RT @seohong_park: Q-learning is not yet scalable. I wrote a blog post about my thoughts on scalable RL algorithms.….
0
187
0
RT @zhuokaiz: My high-level take on why multimodal reasoning is fundamentally harder than text-only reasoning: Language is structured and d….
0
6
0
Revisited @andy_l_jones's RL debugging post from a few years back. Still one of the most insightful guides out there. If your agent's acting weird, here's a great checklist:
2
24
225
✨ Our paper #PlanGenLLMs: A Modern Survey of LLM Planning Capabilities ( is accepted to the #ACL2025 main conference! . Huge thanks to the reviewers for the unanimous 4-4-4 reviews and meta score ❤️ Grateful for your thoughtful feedback! #ACL2025 #NLProc
6
16
152
RT @VioletNPeng: I’ve seen many questions about how to choose ARR tracks for submissions aim at the new tracks at #emnlp2025. We actually w….
0
20
0
Happy to see #EMNLP2025 introducing new tracks on AI/LLM Agents, Code Models, Safety & Alignment, Reasoning, LLM Efficiency, and more. Big thanks to the organizers for making this happen! @emnlpmeeting #NLProc. Perfect venue for agentic research and language technologies.
New AI/LLM Agents Track at #EMNLP2025! . In the past few years, it feels a bit odd to submit agent work to *CL venues because one had to awkwardedly fit it into Question Answering or NLP Applications. Glad to see agent research finally finds home at *CL! . Kudos to the PC for
3
6
69
Just got back from the #ICLR2025 trip, grateful for the conversations, questions, and inspiring talks. Thought I'd share a few reflections from the conference (not exhaustive, just things that stuck with me). 1. Can reasoning learned from code/math generalize to all problems?.
1
16
140
Anyone else going to #ICLR2025? I just learned:. ✈️ Submit your SG Arrival Card (within 3 days before landing (or you'll be doing it at the SIN airport). 🔌 Singapore uses Type G outlets (UK 3-pin), so bring an adapter if needed!. Super excited for ICLR in Singapore! #TravelTips
4
6
111