Yanran Li
@yanranli.bsky.social
📤 16
📥 20
📝 46
PhD student at Columbia University
The work "An uncertainty-aware framework for multi-view animal pose estimation” at
#AAAI26
workshop uses a Multi-view Transformer and a Variance-Inflated Ensemble Kalman Smoother to improve accuracy without needing extra labels. Huge for data-efficient biology research
@aaai.org
7 days ago
0
2
1
Can AI help us settle arguments? 🤖⚖️ Spotted this fascinating poster at
#AAAI26
by researchers from USC and Gachon University. They’re exploring how LLMs can mediate synchronous dispute dialogues, which are often high-emotion and high-conflict.
@aaai.org
7 days ago
0
3
1
This framework, Compare&Generate, at
#AAAI2026
workshop tackles a major hurdle in synthetic data: quality control. Instead of just "thinking step-by-step," the model learns why one output is better than another to iteratively improve.
@aaai.org
7 days ago
0
2
1
Offline RL often fails when agents accidentally drift into Out-of-Distribution (OOD) states. 📉 Fascinating poster at
#AAAI26
on DASP (Density-Aware State Correction). Instead of just suppressing OOD actions, DASP uses a compact variational model to guide agents
@aaai.org
8 days ago
0
2
2
Stop
#AAAI26
to see VisionReward! 🚀 This work introduces a fine-grained reward model that addresses reward hacking in image/video generation. By bridging the gap between interpretable learning and multi-dimensional optimization, they are setting a new standard
@aaai.org
8 days ago
0
1
1
This
#AAAI2026
workshop talk on a new distributional treatment for time series anomaly detection is a paradigm shift—using Isolation Distributional Kernels (IDK). Fascinating to see how IDK^2 maps points through Hilbert spaces to detect group anomalies.
@aaai.org
8 days ago
0
1
1
#AAAI26
on "Local Guidance for Configuration-Based Multi-Agent Pathfinding" (LG-LaCAM)! 🤖🛰️ Tomoki Arita and Keisuke Okumura are pushing the boundaries of MAPF by integrating local guidance into state-of-the-art LaCAM.
@aaai.org
8 days ago
0
3
2
#AAAI26
poster hall: "UMNet: Uncertainty-guided Memory Network for Hyperspectral Pansharpening". 🛰️✨ Xiaozheng Wang and the team at Tiangong University are using spatial-spectral uncertainty-guided loss to solve distortion issues in image fusion.
@aaai.org
8 days ago
0
1
1
at
#AAAI2026
on "RECORd: A Multi-Agent LLM Framework for Reverse Engineering Codebase to Causal Relational Diagram." 👩💻🔍 By using reinforcement fine-tuning (RFT) and multi-agent systems, this work transforms complex code into interpretable causal graphs.
@aaai.org
8 days ago
0
2
1
"Lexicographic Bandits" at
#AAAI2026
! 🎰bridging the gap between Regret Minimization and Best Arm Identification. In complex decision-making systems where objectives have a strict priority, finding the optimal balance is a tough challenge.
@aaai.org
8 days ago
0
1
1
How do we handle the computational burden of streaming data in Gaussian Processes? Some brilliant work on Distributed GP Experts today at
#AAAI26
. By using weighted sums for predictive means and variances, we can keep complexity in check while maintaining accuracy.
@aaai.org
8 days ago
0
1
1
a great talk by Robin van der Laag at
#AAAI26
on "Stochastic multi-objective optimisation." 🎯 Balancing competing objectives in a decision space vs. objective space is a classic challenge. This session provided some great insights into navigating these trade-offs effectively.
@aaai.org
8 days ago
0
3
1
“Flash Embeddings for Online Learning of Categorical Features” at
#AAAI2026
Fascinating approach to learning high-cardinality and recurring categorical data over time—with fixed memory constraints.
@aaai.org
8 days ago
0
1
1
Just attended a fascinating talk on "Bandit Learning in Housing Markets" at
#AAAI2026
🏠📊
@aaai.org
Combining matching theory with multi-armed bandits to learn core allocations—both centralized and decentralized settings with provable regret bounds.
9 days ago
0
4
2
Shift toward using LLMs for both predictions and natural-language explanations is a game-changer for transparency. Seeing impressive results from "TWICE-Rec" on generating high-quality rationales across diverse domains like fashion and scientific research.
#AAAI2026
@aaai.org
9 days ago
0
1
1
Why do LLMs give unreliable recommendations? Often because we lose "evidence strength" during normalization. GUIDER leverages LLM logits to quantify uncertainty and uses a dynamic re-ranking strategy to boost transparency and trust.
#AAAI2026
@aaai.org
9 days ago
0
1
1
Why State-Space Models for event cameras? MA-Mamba proves it! By integrating a Spatio-Temporal Association module, they’ve solved the "noisy & inconsistent" channel update issue in standard SSMs. Great results on DSEC and MVSEC
#AAAI2026
@aaai.org
9 days ago
0
2
1
Deep dive into Hyperspectral Image SR today at
#AAAI2026
. The GEWDiff model uses an edge-aware EDM noise scheduler and a multi-level loss function to ensure structural invariance and stable convergence. Really clean results compared to other SOTA models.
@aaai.org
9 days ago
0
2
1
Fascinated by the "Think-Free" ranking approach (TFRank) presented at
#AAAI2026
! 🚀 It internalizes complex reasoning into small LLMs (<10B), achieving high-accuracy document ranking without the latency of explicit CoT. Practical, efficient, and very impressive.
@aaai.org
9 days ago
0
2
1
Real-time Novel View Synthesis with just 4 cameras? 🤯 Checked out the PHOTONS demo by China Telecom at
#AAAI2026
. It achieves 2K resolution at 25 FPS using a sparse view setup (only 4 RGB cameras).qq.com
@aaai.org
10 days ago
0
1
1
Ready to level up your career? 🚀 Heading to the Job Fair
#AAAI2026
today! If you're looking for new opportunities or a complete career pivot, this is the place to be. Time to network and make things happen! 💼✨
@aaai.org
10 days ago
0
2
1
#AAAI2026
5K Fun Run at 6am 🙋♀️ Can't believe I actually saw the Merlion without its water fountain!
@aaai.org
10 days ago
0
3
1
High-quality Tabular Data Synthesis with Limited Samples! 🚀The team from The University of Melbourne introduced CtrTab at
#AAAI2026
It enhances diffusion models with a novel control mechanism to handle high-dimensional data constraints.📊
@aaai.org
11 days ago
0
2
1
Why treat Time Series as just numbers? 📉🤔 Fascinating talk at
#AAAI2026
on using VLMs for Anomaly Detection:1️⃣ TS models lack 'world knowledge' (context). 2️⃣ LLMs lack 'visual understanding' of shapes.
@aaai.org
Solution: Plot the time series as images!
11 days ago
0
1
1
How do we reconcile Autoregressive vs. One-shot generative paradigms in Time Series? 🤔The TimeCAP presentation at
#AAAI2026
offers a solution: during fine-tuning, we need to balance these complementary strengths while properly modeling multivariate dependencies.
@aaai.org
11 days ago
0
1
1
2nd Invited Talk from Dr. Yolanda Gil at
#AAAI2026
day2 🌟 can not agree more: AI should make us better people!
@aaai.org
11 days ago
0
1
1
2nd Invited Talk from Dr. Yolanda Gil at
#AAAI2026
day2 🌟 can not agree more: AI should make us better people!
@aaai.org
11 days ago
0
1
0
As a
#Zootopia
fan, this poster at
#AAAI2026
is really appealing🤩!🐰🦊
@aaai.org
Very creative design and make me thinking about how to attract other's when making posters
11 days ago
0
1
1
Found a gem for the GP & Causal Inference crowd at
#AAAI2026
! 💎 'CaDyT'—a new framework for Causal Structure Learning in Dynamical Systems. It cleverly uses GP to model continuous-time dynamics from irregularly sampled data, using an MDL score to find causal graph
@aaai.org
11 days ago
0
1
1
Standard RDD breaks when people game the system. At
#AAAI2026
, they propose a Bayesian Mixture Model (BMTM) to handle threshold manipulation in marketing campaigns—effectively separating 'strategic bunching' from organic behavior. A smart fix for causal inference!
@aaai.org
11 days ago
0
2
1
Enjoy the poster session at
#AAAI26
today and some local (?) food from 🇸🇬
@aaai.org
11 days ago
0
2
1
Mind-blowing numbers on LLM inference efficiency at
#AAAI2026
! 📉🚀 The 'Stratos' system manages3,700+ heterogeneous servers. The result? A massive~27x cost reduction and~55% lower latency compared to accuracy-first strategies, all while maintaining Pareto optimality.
@aaai.org
11 days ago
0
3
1
Do VLMs actually 'see' or just rely on priors? 🤔 Fascinating talk by Chirag Agarwal at
#AAAI2026
on Trustworthy Multimodal AI. He showed how models fail to count stripes on a shoe simply because they recognize the 'Adidas' logo and hallucinate the standard 3 stripes.
@aaai.org
11 days ago
0
1
1
Kicking off
#AAAI2026
in Singapore! 🇸🇬 It’s my first time visiting Singapore, and I couldn't be more excited to be here with the AI community.
@aaai.org
11 days ago
2
2
1
Just attended the New Faculty Highlight at
#AAAI2026
featuring Alexander Rodríguez. His work on 'Trustworthy AI for Decision Making in Population Health' tackles the real-world challenges of multimodal data scarcity and noisy signals.
@aaai.org
11 days ago
0
2
1
#AAAI2026
Reception 🙌🏻✨ When: Wednesday, January 21 | 7:30 p.m. – 9:30 p.m. Where: River Wonders, Mandai Wildlife Reserve Attire: Comfortable and casual – wear your walking shoes and dress for warm weather!
@aaai.org
13 days ago
0
1
0
This huge poster do help us a lot for guiding us to the right conference room. Even if whova is convenient, I always prefer a physical agenda.🙋♀️#AAAI2026
13 days ago
2
0
0
about 1 year ago
0
0
0
everyday wake up with...
about 1 year ago
0
0
0
cozy cafe
about 1 year ago
0
0
0
brought all these back to our apartment by hand 💪
about 1 year ago
0
0
0
about 1 year ago
0
0
0
you reached the end!!
feeds!
log in