Katherine Tieu
@kthrn_uiuc
Followers
144
Following
1K
Media
3
Statuses
125
Incoming CS PhD @UofIllinois @ideaisailuiuc | Prev Undergrad @UofIllinois | Graph ML
Joined March 2022
‼️We propose to learn temporal positional encodings for spatial-temporal graphs, L-STEP, in our #ICML2025 paper. Even simple MLPs can achieve leading performance in various temporal link prediction settings!. 📄 Paper: 💻 Code:
0
2
8
RT @deedydas: One of the most important papers in AI: a tiny brain-inspired 27M param model trained on 1000 samples outperforms o3-mini-hig….
0
987
0
RT @TylersNetwork: 📣Join us at the KDD 2025 MLoG-GenAI Workshop! 📣. 🔗 Workshop Website: .📆 Date: Monday, August 4,….
0
5
0
RT @lmthang: Right before #imo2025, together with colleagues from Mountain View, NYC, Singapore, etc, we all gathered at @GoogleDeepMind he….
0
40
0
RT @mihirp98: 🚨 The era of infinite internet data is ending, So we ask:. 👉 What’s the right generative modelling objective when data—not co….
0
174
0
RT @giffmana: AKA data augmentation. The numbers actually match my experience exactly. This is something i think LLM people will slowly red….
0
29
0
RT @pathak2206: Thrilled to finally release this study! 🚀 We view (discrete) diffusion models as implicitly doing data augmentation over au….
0
40
0
RT @SuZhaochen0110: Excited to share our new survey on the reasoning paradigm shift from "Think with Text" to "Think with Image"! 🧠🖼️.Our w….
0
60
0
RT @zhu_zhaocheng: Tips for writing better LLM papers (and increasing your acceptance odds 📈):.1. Report the token cost of your method. 2.….
0
1
0
RT @chelseabfinn: We still lack a scalable recipe for RL post-training seeded with demonstration data. Many methods add an imitation loss,….
0
42
0
RT @giladturok: sometimes ppl forget: flow matching and diffusion are mathematically equivalent!
0
50
0
RT @MuCai7: LLaVA-Prumerge, the first work of Visual Token Reduction for MLLM, finally got accepted after being cited 146 times since last….
0
12
0
RT @wzihanw: 🚀 Introducing Chain-of-Experts (CoE), A Free-lunch optimization method for DeepSeek-like MoE models!. within $200, we explore….
0
164
0
RT @rohanpaul_ai: Today's edition of my newsletter is ready. Consider subscribing, its free and I publish daily with top 1% AI development….
0
3
0
RT @jaseweston: Reasoning, Attention & Memory Workshop @ COLM.Submission Deadline: June 23, 2025 -- Today!.
0
14
0
RT @ZhitingHu: 🔥Reinforcement learning for LLM reasoning is emerging—but many questions remain🧐🧐. ❓ Does RL teach new reasoning, or just el….
0
27
0
RT @VictorKaiWang1: Customizing Your LLMs in seconds using prompts🥳!.Excited to share our latest work with @HPCAILab, @VITAGroupUT, @k_schu….
0
73
0
RT @Synced_Global: Wow, another RL algorithm from ByteDance and it's fast!. T-PPO (Truncated Proximal Policy Optimization) is a new twist o….
0
25
0
RT @tydsh: 📢We show that continuous latent reasoning has a theoretical advantage over discrete token reasoning (:….
arxiv.org
Large Language Models (LLMs) have demonstrated remarkable performance in many applications, including challenging reasoning problems via chain-of-thoughts (CoTs) techniques that generate...
0
172
0