LightNews LightNews
banner
aaai.org
@aaai.org
190 followers 3 following 140 posts
Posts Replies Media Videos
aaai.org
We met so many new and interesting people at AAAI-26. What was your favorite memory?
January 30, 2026 at 12:34 PM
aaai.org
Raise your hand 🙋‍♂️🙋‍♀️if you had fun at student game night during AAAI-26! 👏🙌
January 29, 2026 at 1:37 PM
aaai.org
Attendees at AAAI-26 attended poster sessions throughout the event. With a record number of posters at this year’s conference, there was much opportunity to present, learn, and discuss.
January 28, 2026 at 10:59 PM
Reposted
amazon.science
Thanks to everyone who contributed to a productive @aaai.org conference in Singapore. Our team enjoyed the conversations with researchers and practitioners advancing AI. See you next year! #AAAI2026
January 27, 2026 at 11:20 PM
Reposted
sharky6000.bsky.social
So nice to see photos of AI conferences starting to show up on Bluesky, so please do! (I've already seen a few of @aaai.org that was reposted.)

This was one aspect where LinkedIn was winning at the end of last year. We need more of this! I'll share many of my next one @aamasconf.bsky.social too.
aaai.org aaai.org @aaai.org · 1d
We’ll be sharing some photos from AAAA-26 for the rest of the week. First up, opening reception at Mandi Wilflife Reserve.
January 28, 2026 at 9:00 PM
aaai.org
We’ll be sharing some photos from AAAA-26 for the rest of the week. First up, opening reception at Mandi Wilflife Reserve.
January 28, 2026 at 1:46 PM
Reposted
yanranli.bsky.social
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
January 27, 2026 at 10:11 AM
Reposted
yanranli.bsky.social
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
January 27, 2026 at 10:17 AM
Reposted
yanranli.bsky.social
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
January 27, 2026 at 10:26 AM
Reposted
yanranli.bsky.social
“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
January 25, 2026 at 3:54 PM
Reposted
yanranli.bsky.social
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
January 25, 2026 at 4:02 PM
Reposted
yanranli.bsky.social
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
January 25, 2026 at 4:05 PM
Reposted
yanranli.bsky.social
"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
January 25, 2026 at 4:10 PM
Reposted
yanranli.bsky.social
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
January 25, 2026 at 4:19 PM
Reposted
yanranli.bsky.social
#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
January 25, 2026 at 4:25 PM
Reposted
yanranli.bsky.social
#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
January 25, 2026 at 5:09 PM
Reposted
joebarnby.com
Here we go! #ToM4AI2026 @aaai.org - thanks @reuth-mirsky.bsky.social for the hats 🎩

www.tom4ai.GitHub.io

@nitalon.bsky.social @stefansarkadi.bsky.social
January 26, 2026 at 1:32 AM
Reposted
yanranli.bsky.social
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
January 26, 2026 at 1:48 AM
Reposted
yanranli.bsky.social
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
January 26, 2026 at 1:58 AM
Reposted
yanranli.bsky.social
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
January 26, 2026 at 2:13 AM
Reposted
yanranli.bsky.social
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.
January 25, 2026 at 12:19 PM
Reposted
yanranli.bsky.social
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
January 24, 2026 at 2:51 PM
Reposted
yanranli.bsky.social
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
January 24, 2026 at 2:58 PM
Reposted
yanranli.bsky.social
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
January 24, 2026 at 3:30 PM
Reposted
yanranli.bsky.social
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
January 24, 2026 at 4:36 PM