Singapore

The safety alignment of large language models (LLMs) often relies on reinforcement learning from human feedback (RLHF), which requires human annotations to construct preference datasets. Given the challenge of assigning overall quality scores to data, recent works increasingly adopt fine-grained ratings based on multiple safety rules. In this paper, we discover a robust phenomenon: Rules with higher rating entropy tend to have lower accuracy in distinguishing human-preferred responses. Exploiting this insight, we propose ENCORE, a simple entropy-guided method to compose multi-head rewards by penalizing rules with high rating entropy. Theoretically, we show that such rules yield negligible weights under the Bradley–Terry loss during weight optimization, naturally justifying their penalization. Empirically, ENCORE consistently outperforms strong baselines, including random and uniform weighting, single-head Bradley–Terry, and LLM-as-a-judge, etc. on RewardBench safety tasks. Our method is completely training-free, generally applicable across datasets, and retains interpretability, making it a practical and effective approach for multi-attribute reward modeling.

AAAI 2026

ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models

reward models

llm-as-a-judge

rlhf

large language models

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

poster

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.

To access this event page, you need to log in with the **email address you registered with**. 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.

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias problem, limiting their ability to retain high-frequency information, and often struggle with noise robustness. Motivated by recent trends in iterative refinement processes, we propose Iterative Implicit Neural Representations (I-INRs), a novel plug-and-play framework that iteratively refines signal reconstructions to restore high-frequency details, improve noise robustness, and enhance generalization, ultimately delivering superior reconstruction quality. I-INRs integrate seamlessly into existing INR architectures with only a 0.5–2\% increase in parameters. During reconstruction, the iterative refinement adds just 0.8–1.6\% additional FLOPs over the baseline while delivering a substantial performance boost of up to +2.0 PSNR. Extensive experiments demonstrate that I-INRs consistently outperform WIRE, SIREN, and Gauss across diverse computer-vision tasks, including image fitting, image denoising, and object-occupancy prediction.

I-INR: Iterative Implicit Neural Representations

Stochastic dynamical systems have emerged as fundamental models across numerous application domains, providing powerful mathematical representations for capturing uncertain system behavior. In this paper, we address the problem of runtime safety and reach-avoid probability prediction for discrete-time stochastic systems with online observations, i.e., estimating the probability that the system satisfies a given safety or reach-avoid specification. Unlike traditional approaches that rely solely on offline models, we propose a framework that incorporates real-time observations to dynamically refine probability estimates for safety and reach-avoid events. By introducing observation-aware barrier functions, our method adaptively updates probability bounds as new observations are collected, combining efficient offline computation with online backward iteration. This approach enables rigorous and responsive prediction of safety and reach-avoid probabilities under uncertainty. In addition to the theoretical guarantees, experimental results on benchmark systems demonstrate the practical effectiveness of the proposed method.

Runtime Safety and Reach-avoid Prediction of Stochastic Systems via Observation-aware Barrier Functions

Large Language Models (LLMs) have achieved impressive performance in complex reasoning problems. Their effectiveness highly depends on the specific nature of the task, especially the required domain knowledge. Existing approaches, such as mixture-of-experts, typically operate at the task level; they are too coarse to effectively solve the heterogeneous problems involving multiple subjects. This work proposes a novel framework that performs fine-grained analysis at subject level equipped with a designated multi-agent collaboration strategy for addressing heterogeneous problem reasoning. Specifically, given an input query, we first employ a Graph Neural Network to identify the relevant subjects and infer their interdependencies to generate an Subject-based Directed Acyclic Graph (S-DAG), where nodes represent subjects and edges encode information flow. Then we profile the LLM models by assigning each model a subject-specific expertise score, and select the top-performing one for matching corresponding subject of the S-DAG. Such subject-model matching enables graph-structured multi-agent collaboration where information flows from the starting model to the ending model over S-DAG. We curate and release multi-subject subsets of standard benchmarks (MMLU-Pro, GPQA, MedMCQA) to better reflect complex, real-world reasoning tasks. Extensive experiments show that our approach significantly outperforms existing task-level model selection and multi-agent collaboration baselines in accuracy and efficiency. These results highlight the effectiveness of subject-aware reasoning and structured collaboration in addressing complex and multi-subject problems.

S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning

Dynamic LiDAR point cloud compression (LPCC) is crucial for the efficient transmission and storage of large-scale three-dimensional data in applications such as autonomous driving. However, many existing methods, which primarily focus on compressing geometric or motion information, face a fundamental limitation: they treat all points as equally important. This approach neglects the semantic priorities of a scene, resulting in inefficient bit allocation and particularly compromising the reconstruction quality of safety-critical regions, such as pedestrians and vehicles, which are vital to downstream perception tasks. To address these limitations, we propose R²D-LPCC, a relevance-ranking framework for region-adaptive LPCC that prioritizes fidelity in semantically important regions. Central to our approach is the Adaptive Relevance Learning (ARL) module, which integrates semantic context with uncertainty to evaluate regional significance and guide compression. We also introduce a Multi-scale Region-Adaptive Transform (MRAT) module to enhance semantic feature modeling and preserve fine-grained details in key areas. Additionally, we develop an adaptive multimodal motion estimation module to improve motion prediction in complex three-dimensional environments. Extensive experiments conducted on the SemanticKITTI benchmark demonstrate that R²D-LPCC significantly surpasses ten recent state-of-the-art methods, achieving a 45.48$\%$ BD-rate gain over the previous leading method, Unicorn, and a 98.58$\%$ gain over the GPCC standard, while ensuring superior reconstruction quality in semantically important regions.

R²D-LPCC: Relevance-Ranking Guided Region-Adaptive Dynamic LiDAR Point Cloud Compression

Solving energy-saving distributed heterogeneous flexible job shop scheduling problem (ES-DHFJSP) aims to enhance industrial production efficiency while minimizing energy consumption. State-of-the-art co-evolutionary algorithms have emerged as effective approaches for addressing ES-DHFJSP. However, existing methodologies demonstrate compromised convergence rates and excessive computational overhead when confronted with vast search spaces. In this work, we propose a novel solution space transformation-guided co-evolution algorithm (SSTCE) to overcome this limitation. In SSTCE, we first establish an inter-job similarity metric and incorporate constrained hierarchical clustering with optimal leaf ordering (CHC-OLO) to generate clustered job sets, which are subsequently utilized for population initialization that achieves a favorable balance between convergence and diversity. To enhance search capability in expansive solution spaces, we devise a dynamic solution space transformation mechanism that effectively reduces inefficient searches within the algorithm. Furthermore, we develop tailored local search strategies leveraging domain-specific knowledge of DHFJSP properties. Extensive experimental evaluations across 20 benchmark instances demonstrate that SSTCE significantly outperforms existing evolutionary algorithms in solving ES-DHFJSP.

A Solution Space Transformation-Guided Co-Evolution for Energy-Saving Distributed Heterogeneous Flexible Job Shop Scheduling

Recently, video-language models (VidLMs) have gained widespread attention and adoption. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation benchmark which is build through a collaborative approach combining human expertise and AI models. To ensure data quality, we have conducted in-depth considerations from multiple perspectives. First, to address the unique challenges of underwater environments, we selected videos that represent typical underwater challenges including light variations, water turbidity, and diverse viewing angles to construct the dataset. Second, to ensure data diversity, the dataset covers a wide range of frame rates, resolutions, 419 classes of marine animals, and various static plants and terrains. Next, for task diversity, we adopted a structured design where observation targets are categorized into two major classes: biological and environmental. Each category includes content observation and change/action observation, totaling 20 subtask types. Finally, we designed several challenging evaluation metrics to enable quantitative comparison and analysis of different methods. Experiments on two representative VidLMs demonstrate that fine-tuning VidLMs on UVLM significantly improves underwater world understanding while also showing potential for slight improvements on existing in-air VidLM benchmarks, such as VideoMME and Perception text. The dataset and prompt engineering will be released publicly.

UVLM: Benchmarking Video Language Model for Underwater World Understanding

Traditional dialogue retrieval aims to select the most appropriate utterance or image from recent dialogue history. However, they often fail to meet users’ actual needs for revisiting semantically coherent content scattered across long-form conversations. To fill this gap, we define the Fine-grained Fragment Retrieval (FFR) task, requiring models to locate query-relevant fragments, comprising both utterances and images, from multimodal long-form dialogues. As a foundation for FFR, we construct MLDR, the longest-turn multimodal dialogue retrieval dataset to date, averaging 25.45 turns per dialogue, with each naturally spanning three distinct topics. To evaluate generalization in real-world scenarios, we curate and annotate a WeChat-based test set comprising real-world multimodal dialogues with an average of 75.38 turns. Building on these resources, we explore existing generation-based Vision-Language Models (VLMs) on FFR and observe that they often retrieve incoherent utterance-image fragments. While optimized for generating responses from visual-textual inputs, these models lack explicit supervision to ensure semantic coherence within retrieved fragments. To address this, we propose F$^2$RVLM, a generative retrieval model trained in a two-stage paradigm: (1) supervised fine-tuning to inject fragment-level retrieval knowledge, and (2) GRPO-based reinforcement learning with multi-objective rewards to encourage outputs with semantic precision, relevance, and contextual coherence. In addition, to account for difficulty variations arising from differences in intra-fragment element distribution, ranging from locally dense to sparsely scattered, we introduce a difficulty-aware curriculum sampling that ranks training instances by predicted difficulty and gradually incorporates harder examples. This strategy enhances the model’s reasoning ability in long, multi-turn dialogue contexts. Experiments on both in-domain and real-domain sets demonstrate that F$^2$RVLM substantially outperforms popular VLMs, achieving superior retrieval performance.

F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model

The low sampling efficiency during the rollout phase poses a significant challenge to scaling reinforcement learning for large language model reasoning. Existing methods attempt to improve efficiency by scheduling problems based on problem difficulties. However, these approaches suffer from unstable and biased estimations of problem difficulty and fail to capture the alignment between model competence and problem difficulty in RL training, leading to suboptimal results. To address these challenges, we introduce $\textbf{C}$ompetence-$\textbf{D}$ifficulty $\textbf{A}$lignment $\textbf{S}$ampling ($\textbf{CDAS}$). This approach allows for accurate and stable estimation of problem difficulties by aggregating historical performance discrepancies across problems. Subsequently, model competence is quantified to adaptively select problems whose difficulties align with the model's current competence using a fixed-point system. Extensive experiments in mathematical RL training show that $\textbf{CDAS}$ consistently outperforms strong baselines, achieving the highest average accuracy of 45.89\%. Furthermore, $\textbf{CDAS}$ reduces the training step time overhead by 57.06\% compared to the widely-used Dynamic Sampling strategy, verifying the efficiency of $\textbf{CDAS}$. Additional experiments on different tasks, model architectures, and model sizes demonstrate the generalization capability of $\textbf{CDAS}$.

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective

Depth-wise pruning accelerates LLM inference in resource-constrained scenarios but suffers from performance degradation due to indiscriminate removal of entire Transformer layers. This paper reveals ``Patch-Like'' redundancy across layers via correlation analysis of the outputs of different layers in reproducing kernel Hilbert space, demonstrating consecutive layers exhibit high functional similarity. Building on this observation, this paper proposes Sliding-Window Merging (SWM) - a dynamic compression method that selects consecutive layers from top to bottom using a pre-defined similarity threshold, and compacts patch-redundant layers through a parameter consolidation, thereby simplifying the model structure while maintaining its performance. Extensive experiments on LLMs with various architectures and different parameter scales show that our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning. In particular, in the experiment with 35\% pruning on the Vicuna-7B model, our method achieved a 1.654\% improvement in average performance on zero-shot tasks compared to the existing method. Moreover, we further reveal the potential of combining depth pruning with width pruning to enhance the pruning effect.

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs

The performance of egocentric AI agents is fundamentally limited by multimodal intent ambiguity. This challenge arises from a combination of underspecified language, imperfect visual data, and deictic gestures, which frequently leads to task failure. Existing monolithic Vision-Language Models (VLMs) struggle to resolve these multimodal ambiguous inputs, often failing silently or hallucinating responses. To address these ambiguities, we introduce the Plug-and-Play Clarifier, a zero-shot and modular framework that decomposes the problem into discrete, solvable sub-tasks. Specifically, our framework consists of three synergistic modules: (1) a text clarifier that uses dialogue-driven reasoning to interactively disambiguate linguistic intent, (2) a vision clarifier that delivers real-time guidance feedback, instructing users to adjust their positioning for improved capture quality, and (3) a cross-modal clarifier with grounding mechanism that robustly interprets 3D pointing gestures and identifies the specific objects users are pointing to. Extensive experiments demonstrate that our framework improves the intent clarification performance of small language models (4--8B) by approximately 30\%, making them competitive with significantly larger counterparts. We also observe consistent gains when applying our framework to these larger models. Furthermore, our vision clarifier increases corrective guidance accuracy by over 20\%, and our cross-modal clarifier improves semantic answer accuracy for referential grounding by 5\%. Overall, our method provides a plug-and-play framework that effectively resolves multimodal ambiguity and significantly enhances user experience in egocentric interaction.

Downloads

Next from AAAI 2026

I-INR: Iterative Implicit Neural Representations

Similar lecture

RewardBench: Evaluating Reward Models for Language Modeling

.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

I-INR: Iterative Implicit Neural Representations

Similar lecture

RewardBench: Evaluating Reward Models for Language Modeling

Downloads