Yanran Li

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

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

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

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

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

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

#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

#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

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

"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

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

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

“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

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.

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

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

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

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

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

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

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

#AAAI2026 5K Fun Run at 6am 🙋‍♀️ Can't believe I actually saw the Merlion without its water fountain! @aaai.org

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

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!

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

2nd Invited Talk from Dr. Yolanda Gil at #AAAI2026 day2 🌟 can not agree more: AI should make us better people! @aaai.org

2nd Invited Talk from Dr. Yolanda Gil at #AAAI2026 day2 🌟 can not agree more: AI should make us better people! @aaai.org

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

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

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