Singapore

Recent research reveals that a minority of high-entropy tokens significantly influences the reasoning quality of large language models (LLMs). Inspired by this, we propose Prototype Entropy Alignment (PEA), a reinforcement learning framework that models effective reasoning not as a single path, but as a collection of learnable &quot;entropy signatures.&quot; PEA identifies these signatures by clustering the uncertainty patterns of expert trajectories into a dynamic set of prototypes. It then rewards the model for aligning its own reasoning process with these evolving targets, creating a self-improving loop. Instead of replacing traditional outcome-based rewards, PEA provides a complementary, process-oriented signal. Our experiments show this synergy is crucial: PEA substantially boosts performance on creative and general reasoning tasks, and when combined with outcome rewards, achieves state-of-the-art results on structured tasks like mathematics. By rewarding alignment with diverse and evolving reasoning structures, PEA offers a robust, verifier-free pathway to enhance the depth and adaptability of LLM reasoning.

AAAI 2026

Prototype Entropy Alignment: Reinforcing Structured Uncertainty in LLM Reasoning

entropy-based learning

policy optimization

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

Recent research reveals that a minority of high-entropy tokens significantly influences the reasoning quality of large language models (LLMs). Inspired by this, we propose Prototype Entropy Alignment (PEA), a reinforcement learning framework that models effective reasoning not as a single path, but as a collection of learnable "entropy signatures." PEA identifies these signatures by clustering the uncertainty patterns of expert trajectories into a dynamic set of prototypes. It then rewards the model for aligning its own reasoning process with these evolving targets, creating a self-improving loop. Instead of replacing traditional outcome-based rewards, PEA provides a complementary, process-oriented signal. Our experiments show this synergy is crucial: PEA substantially boosts performance on creative and general reasoning tasks, and when combined with outcome rewards, achieves state-of-the-art results on structured tasks like mathematics. By rewarding alignment with diverse and evolving reasoning structures, PEA offers a robust, verifier-free pathway to enhance the depth and adaptability of LLM reasoning.

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

3D single object tracking (SOT) in LiDAR point clouds is a critical task in computer vision and autonomous driving. Despite great success having been achieved, the inherent sparsity of point clouds introduces a dual-redundancy challenge that limits existing trackers: (1) vast spatial redundancy from background noise impairs accuracy, and (2) informational redundancy within the foreground hinders efficiency. To tackle these issues, we propose **CompTrack**, a novel end-to-end framework that systematically eliminates both forms of redundancy in point clouds. First, CompTrack incorporates a Spatial Foreground Predictor (SFP) module to filter out irrelevant background noise based on information entropy, addressing spatial redundancy. Subsequently, its core is an Information Bottleneck-guided Dynamic Token Compression (IB-DTC) module that eliminates the informational redundancy within the foreground. Theoretically grounded in low-rank approximation, this module leverages an online SVD analysis to adaptively compress the redundant foreground into a compact and highly informative set of proxy tokens. Extensive experiments on KITTI, nuScenes and Waymo datasets demonstrate that CompTrack achieves top-performing tracking performance with superior efficiency, running at a real-time 90 FPS on a single RTX 3090 GPU.

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effectiveness in general domains and medical QA tasks, little attention has been paid to KE in multimodal medical scenarios. Unlike text-only settings, medical KE demands integrating updated knowledge with visual reasoning to support safe and interpretable clinical decisions. To address this gap, we propose MultiMedBench, the first benchmark tailored to
evaluating KE in clinical multimodal tasks. Our framework spans both understanding and reasoning task types, defines a three-dimensional metric suite (reliability, generality, and locality), and supports cross-paradigm comparisons across general and domain-specific models. We conduct extensive experiments under single-editing and lifelong-editing settings. Results suggest that current methods struggle with generalization and long-tail reasoning, particularly in complex clinical workflows. We further present an efficiency analysis (e.g., edit latency, memory footprint), revealing practical trade-offs in real-world deployment across KE paradigms. Overall, MultiMedBench not only reveals the limitations of current approaches but also provides a solid foundation for developing clinically robust knowledge editing techniques in the future.

MultiMedBench: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA

Conversational Recommender Systems (CRS) aim to provide personalized recommendations by interacting with users through natural language dialogue. However, in scenarios requiring deep geospatial awareness, existing methods, including those based on Large Language Models (LLMs), still face significant challenges in effectively fusing heterogeneous, multimodal geographic information with dynamic dialogue context. Simple fusion strategies struggle to resolve the asymmetric dependencies between dynamic user intent and static geographic context and fail to bridge the semantic gap between LLMs and structured geospatial data. To address these issues, we propose a framework for geography-aware CRS, named GeoCRS. Our core idea is to empower a frozen LLM with powerful geospatial reasoning capabilities by conditioning it on a dynamic, multimodal guidance signal generated by an external fusion architecture, all without altering the LLM's internal parameters. Specifically, we first design a hierarchical geographical encoder to uniformly represent heterogeneous geographic data. Subsequently, we introduce a contextual feature modulation module that asymmetrically injects the geographic context into the user's dialogue intent via a novel modulation mechanism to improve conversational recommendation via both geographic and dialogue context. Extensive experiments on public benchmark datasets demonstrate that our proposed GeoCRS significantly outperforms state-of-the-art baselines on the geography-aware conversational recommendation task.

From Dialogue to Destination: Geography-Aware Large Language Models with Multimodal Fusion for Conversational Recommendation

Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and background, recognizing actions in such samples remains challenging because of the background distractions. Receptance Weighted Key Value (RWKV), which learns interaction between various dimensions, shows promise for global modeling. While directly applying RWKV to wide-angle FSAR may fail to highlight subjects due to excessive background information. Additionally, temporal relation degraded by frames with similar backgrounds is difficult to reconstruct, further impacting performance. Therefore, we design the CompOund SegmenTation and Temporal REconstructing RWKV (Otter). Specifically, the Compound Segmentation Module (CSM) is devised to segment and emphasize key patches in each frame, effectively highlighting subjects against background information. The Temporal Reconstruction Module (TRM) is incorporated into the temporal-enhanced prototype construction to enable bidirectional scanning, allowing better reconstruct temporal relation. Furthermore, a regular prototype is combined with the temporal-enhanced prototype to simultaneously enhance subject emphasis and temporal modeling, improving wide-angle FSAR performance. Extensive experiments on benchmarks such as SSv2, Kinetics, UCF101, and HMDB51 demonstrate that Otter achieves state-of-the-art performance. Extra evaluation on the VideoBadminton dataset further validates the superiority of Otter in wide-angle FSAR.

Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV

Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens of thousands of training samples. However, most existing optimizers struggle to perform effectively at such a large batch size. 
As batch size increases, gradient noise decreases due to averaging over many samples, limiting the ability of first-order methods to escape sharp or suboptimal minima and reach the global minimum.
Meanwhile, second-order methods like the natural gradient with Kronecker-Factored Approximate Curvature (KFAC) often require excessively high damping to remain stable at large batch sizes. This high damping effectively ``washes out" the curvature information that gives these methods their advantage, reducing their performance to that of simple gradient descent.
In this paper, we introduce Fisher-Orthogonal Projection (FOP), a novel technique that restores the effectiveness of the second-order method at very large batch sizes, enabling scalable training with improved generalization and faster convergence.
FOP constructs a variance-aware update direction by leveraging gradients from two sub-batches, enhancing the average gradient with a component of the gradient difference that is orthogonal to the average under the Fisher-metric. 
Through extensive benchmarks, we show that FOP accelerates convergence by $\times1.2–1.3$ over K-FAC and $\times1.5–1.7$ over SGD/AdamW at the same moderate batch sizes, while at extreme scales it achieves up to a $\times7.5$ speedup. 
Unlike other methods, FOP maintains small-batch accuracy when scaling to extremely large batch sizes. Moreover, it reduces Top-1 error by 2.3–3.3\% on long-tailed CIFAR benchmarks, demonstrating robust generalization under severe class imbalance. Our lightweight, geometry-aware use of intra-batch variance makes natural-gradient optimization practical on modern data-centre GPUs. FOP is open-source and pip-installable, which can be integrated into existing training code with a single line and no extra configuration.

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training

Neural algorithmic reasoning, a term first coined by DeepMind, has recently emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state represents the intermediate outcome after an execution step. The training objective is to generate state sequences that accurately replicate the underlying algorithmic process. A common framework for this task adopts an "encoder-processor-decoder" architecture, where the encoder learns representations of states, the processor simulates algorithmic steps, and the decoder reconstructs output states. While prior work has primarily focused on improving the processor, the role of the encoder in representation learning has received relatively little attention. Most existing approaches rely on simple MLP-based encoders, raising the question of whether such representations are sufficiently informative for supporting algorithmic reasoning.

This paper investigates how to improve encoder representations for neural algorithmic reasoning. We propose a reconstruction module that aims to recover the input state from its encoded representation. This auxiliary reconstruction task encourages the encoder to retain critical information about the input. We demonstrate that incorporating this task during training improves the performance of existing neural architectures on standard benchmarks. Furthermore, we observe that current encoders often underutilize the correlations among features within a state. To address this, we draw inspiration from self-supervised learning and design an enhanced variant of the auxiliary task that encourages the encoder to capture intra-state feature dependencies. Experimental results show that our method enables the encoder to learn richer representations, thereby enhancing the performance of existing processors on algorithmic reasoning tasks.

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction

We consider a problem of offline reinforcement learning from human feedback (RLHF) with pairwise comparisons proposed by Zhu et al. (2023), where the implicit reward is a linear function of an unknown parameter. Given an offline dataset, our objective consists in ascertaining the optimal action for each state, with the ultimate goal of minimizing the {\em simple regret}. We propose an algorithm, \underline{RL} with \underline{L}ocally \underline{O}ptimal \underline{W}eights or {\sc RL-LOW}, which yields an exponential form of simple regret of $\exp ( - \Omega(n/H) )$ where $n$ is the number of data samples and $H$ denotes an instance-dependent hardness quantity that depends explicitly on the suboptimality gap of each action. Furthermore, we derive a first-of-its-kind instance-dependent lower bound in offline RLHF with pairwise comparisons. Interestingly, we observe that the lower and upper bounds on the simple regret match order-wise in the exponent, demonstrating order-wise optimality of our {\sc RL-LOW}. 
In view of privacy considerations in practical applications, we also extend {\sc RL-LOW} to the setting of $(\varepsilon,\delta)$-differential privacy and show, somewhat surprisingly, that the hardness parameter $H$ is unchanged in the asymptotic regime as $n$ tends to infinity; this underscores the inherent efficiency of {\sc RL-LOW} in terms of preserving the privacy of the observed rewards. Given our focus on establishing instance-dependent bounds of exponential convergence, our research fills the research gap in existing studies that concentrate on establishing worst-case regrets of {\em inverse polynomial convergence} (e.g., $\widetilde{O}(\frac{1}{\sqrt{n}})$) for offline RLHF with pair-wise comparison.

On the Exponential Convergence for Offline RLHF with Pairwise Comparisons

Given a non-negative integer $\ell$, the $k$-median with outliers problem extends the standard $k$-median problem by allowing the removal of up to $\ell$ points and minimizing the clustering cost over the remaining ones. Algorithmic development in this setting remains an active area of research due to its relevance in processing noisy data. In this paper, we present a sampling-based reduction from the $k$-median with outliers problem to its outlier-free counterpart. The reduction incurs a multiplicative overhead of $(k\ell^{-1} + \varepsilon^{-1})^{O(\ell)}$ in the running time and an arbitrarily small loss in the approximation ratio. This improves upon previously known reductions with overheads of $((k + \ell)\varepsilon^{-1})^{O(\ell)}n^{O(1)}$ and $((k + \ell)\varepsilon^{-1})^{O(\ell)}$, given by Agrawal et al. (AAAI 2023) and Jaiswal and Kumar (ISAAC 2023), respectively. As applications, we obtain faster fixed-parameter tractable (FPT) algorithms with tight approximation guarantees for the $k$-median with outliers problem under various metric spaces. Furthermore, our approach naturally generalizes to constrained variants of the problem where additional constraints are imposed on the cluster sizes, and yields similar improvements in their FPT approximations.

A More Efficient Reduction from Outlier-Aware to Outlier-Free k-Median

Food rescue organizations simultaneously tackle food insecurity and waste by working with volunteers to redistribute food from donors who have excess to recipients who need it. Volunteer feedback allows food rescue organizations to identify issues early and ensure volunteer satisfaction. However, food rescue organizations monitor feedback manually, which can be cumbersome and labor-intensive, making it difficult to prioritize which issues are most important. In this work, we investigate how large language models (LLMs) assist food rescue organizers in understanding and taking action based on volunteer experiences. We work with 412 Food Rescue, a large food rescue organization based in Pittsburgh, Pennsylvania, to design RescueLens, an LLM-powered tool that automatically categorizes volunteer feedback, suggests donors and recipients to follow up with, and updates volunteer directions based on feedback. We evaluate the performance of RescueLens on an annotated dataset, and show that it can recover 96% of volunteer issues at 71% precision. Moreover, by ranking donors and recipients according to their rates of volunteer issues, RescueLens allows organizers to focus on 0.5% of donors responsible for more than 30% of volunteer issues. RescueLens is now deployed at 412 Food Rescue and through semi-structured interviews with organizers, we find that RescueLens streamlines the feedback process so organizers better allocate their time.

RescueLens: LLM-Powered Triage and Action on Volunteer Feedback for Food Rescue

Industrial data scientists modeling an asset's condition need to build domain understanding by asking questions about a given asset. Some example asset questions are what failure modes can it experience, under which operating conditions, and how the manufacturer and weather affect.
Traditionally, the main source of domain information comes from Subject Matter Experts (SMEs) and Failure Modes and Effects Analysis (FMEA) documents which are not always available and may not be detailed enough to cover different external factors (e.g., operating mode, manufacturer, weather). 
Now that Large Language Models (LLMs) have became a commodity, this gives us a big opportunity to leverage them to bridge this gap. 
Inspired by other's work on LLM knowledge probing, we present a Multi-Agent System (MAS) specialized on aiding industrial data scientists guide their modeling decisions. One challenge we address is the generated linguistic diversity and question relevance, which we optimize by using popular information diversity metrics and a grounded relevancy classifier. 
We continuously monitor the set of newly generated instruction sets at the end of each round, compare the linguistic diversity against common baselines and show high generated knowledge coverage on the downstream FMEA task.
We also conduct user studies to validate the quality of the questions. 
We finally present the real-world implications of providing diverse asset specific information to aid data scientist's modeling decisions through our deployed MAS. 
Through the deployed system, we show its generalizability to different assets and extendibility to more downstream tasks like work order scheduling, failure mode sensor analysis and machine learning model recipes generation.

Downloads

Next from AAAI 2026

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

Similar lecture

PEA+IDA: An Improved Hybrid Memory-Restricted Algorithm

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking

Similar lecture

PEA*+IDA*: An Improved Hybrid Memory-Restricted Algorithm

Downloads

PEA+IDA: An Improved Hybrid Memory-Restricted Algorithm