Singapore

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. While multi-head self-attention (MHA) has proven critical in many areas, its role in multilingual capabilities remains underexplored. In this work, we study the contribution of MHA in supporting multilingual processing in LLMs. We propose Language Attention Head Importance Scores (LAHIS), an effective and efficient method that identifies attention head importance for multilingual capabilities via a single forward and backward pass through the LLM. Applying LAHIS to Aya-23-8B, Llama-3.2-3B, and Mistral-7B-v0.1, we reveal the existence of both language-specific and language-general heads. Language-specific heads enable cross-lingual attention transfer to guide the model toward target language contexts and mitigate off-target language generation issue, contributing to addressing challenges in multilingual LLMs. We also introduce a lightweight adaptation that learns a soft head mask to modulate attention outputs over language heads, requiring only 20 tunable parameters to improve XQuAD accuracy. Overall, our work enhances both the interpretability and multilingual capabilities of LLMs from the perspective of MHA.

AAAI 2026

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

multi-head self attention

multilingual llm

interpretability

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

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.

Strategyproofness has been the holy grail in mechanism design for decades, providing strong incentive compatibility guarantees under the assumption of perfectly rational agents. However, this assumption is questionable when agents exhibit bounded rationality. Moreover, strategyproofness often imposes strong impossibility results that prevent mechanisms from surpassing certain approximation barriers. We study this tension in budget-feasible mechanism design, where a designer wants to procure services of maximum value from agents subject to a budget constraint. Here, strategyproofness imposes approximation barriers of $1+\sqrt{2}$ and $2$ for deterministic and randomized mechanisms, respectively.

We investigate how much we can potentially gain under bounded rationality. We adopt the weaker notion of \emph{not obviously manipulable (NOM)}, which only prevents "obvious" strategic deviations. We fully resolve the achievable approximation guarantees under NOM: We derive a deterministic $2$-approximate NOM mechanism under the general class of monotone subadditive valuations.
We also show that this bound is tight (even for additive valuations). Additionally, we provide a simple randomized $(1+\varepsilon)$-approximate NOM mechanism for any $\varepsilon > 0$. These results demonstrate a clear separation between strategyproof and NOM mechanisms. Our mechanisms use \emph{Golden Tickets} and \emph{Wooden Spoons} as natural design primitives, arising from our characterization of NOM mechanisms.

Breaking Barriers, Finding Boundaries: Not Obviously Manipulable Budget-Feasible Mechanism Design

Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an under-explored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.

EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering

Given an undirected graph and a size parameter $k$, the Densest $k$-Subgraph (D$k$S) problem extracts the subgraph on $k$ vertices with the largest number of induced edges. While D$k$S is NP--hard and difficult to approximate, penalty-based continuous relaxations of the problem have recently enjoyed practical success for real-world instances of D$k$S. In this work, we propose a scalable and exact continuous penalization approach for D$k$S using the error bound principle, which enables the design of suitable penalty functions. Notably, we develop new theoretical guarantees ensuring that both the global and local optima of the penalized problem match those of the original problem. The proposed penalized reformulation enables the use of first-order continuous optimization methods. In particular, we develop a non-convex proximal gradient algorithm, where the non-convex proximal operator can be computed in closed form, resulting in low per-iteration complexity. We also provide convergence analysis of the algorithm. Experiments on large-scale instances of the D$k$S problem and one of its variants, the Densest ($k_1, k_2$) Bipartite Subgraph (D$k_1k_2$BS) problem, demonstrate that our method achieves a favorable balance between computation cost and solution quality.

A Scalable and Exact Relaxation for Densest k-Subgraph via Error Bounds

Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cost of longer chain of thought (CoT), hampering interaction efficiency in real-world scenarios. Nevertheless, there still lacks systematic definition of LLM‑Agent efficiency, hindering targeted improvements. 
To this end, we introduce dual‑efficiency, comprising 
(i) step-level efficiency, which minimizes tokens per step, and (ii) trajectory-level efficiency, which minimizes the number of steps to complete a task. 
Building on this definition, we propose **DEPO**, a dual-efficiency preference‑based optimization method that jointly rewards succinct responses and fewer action steps. Experiments on WebShop and BabyAI show that **DEPO** cuts token usage by up to 60.9\% and steps by up to 26.9\%, while achieving up to a 29.3\% improvement in task performance. **DEPO** also generalizes to three out-of-domain math benchmarks and retains its efficiency gains when trained on only 25\% of the data. The code is available in Appendix.

DEPO: Dual-Efficiency Preference Optimization for LLM Agents

Bipartite learning is a machine learning task aimed at predicting interactions among pairs of instances. It has been applied to a variety of domains, including drug-target interaction, RNA-disease association and regulatory network inference. Despite widely investigated, current methods still present drawbacks, as they are often designed for a specific application and thus do not generalize to other problems, or present scalability issues. To address these challenges, we propose Oxytrees: proxy-based biclustering model trees. Oxytrees compress the interaction matrix into row- and column-wise proxy matrices to significantly reduce training time without impacting predictive performance. We also propose a new leaf-assignment algorithm that significantly reduces the time taken for prediction. Finally, Oxytrees employ linear models using the Kronecker product kernel in their leaves, resulting in shallower trees and thus even faster training. Using 15 datasets, we compared the predictive performance of ensembles of Oxytrees against the current state-of-the-art. We achieve up to 30-fold improvement in training times against the state-of-the-art biclustering forests, while showing competitive or superior performance in most evaluation settings, especially in the inductive setting. Finally, we provide an intuitive Python API to access all datasets, methods and evaluation measures used in this work, thus enabling reproducible research in this field.

Oxytrees: Model Trees for Bipartite Learning

Graph Neural Networks (GNNs) have effectively improved the performance of Cognitive Diagnosis Models (CDMs). Existing works have proposed a series of Graph-based Cognitive Diagnosis Frameworks (GCDFs) to enhance robustness to noise. However, these robust designs are often general methods for GNNs and are not designed for cognitive diagnosis, which undermines real cognitive information during the denoising process. Interestingly, a noteworthy phenomenon has been overlooked: even without robustness designs, GCDFs can still learn correct information in noisy environments. In this paper, we conduct a comprehensive empirical analysis of this issue. We found that noise primarily accumulates in lower singular components. Even in noisy environments, the principal subspaces of representations still remain stable. Based on these findings, we propose a Noise-aware Cognitive Diagnostic framework based on Low-rank Alignment, named NCDLA. The framework first performs low-rank reconstruction of the interaction matrix between students and exercises, retaining only larger singular values to achieve noise reduction. Then, the reconstructed interaction matrix and the original interaction matrix are combined with the Q matrix to form a noise-reduced heterogeneous graph and an original heterogeneous graph. In order to distinguish between the interaction patterns of correct and incorrect responses, we decompose the heterogeneous graph according to the type of response. NCDLA achieves denoising of student representations and exercises representations through a self-supervised strategy based on low-rank reconstruction and a spectral anchor regularisation method. Extensive experiments on three datasets demonstrate that NCDLA achieves optimal prediction performance and robustness.

Noise-Aware Graph-Based Cognitive Diagnostic Framework Through Low-Rank Alignment

The text-to-SQL task is an active challenge in Natural Language Processing. Many existing solutions focus on using black-box language models extended with specialized components within customized end-to-end text-to-SQL pipelines. While these solutions use both closed-source proprietary language models and coding-oriented open-source models, there is a lack of research regarding SQL-specific small generative models. At the same time, recent advancements in self-correcting generation strategies show promise for improving the capabilities of existing architectures. The application of these concepts to the text-to-SQL task remains unexplored.
In this paper, we introduce RetrySQL, a new approach to training text-to-SQL generation models. We prepare reasoning steps for reference SQL queries and then corrupt them to create retry data that contains both incorrect and corrected steps, divided with a special token. We continuously pre-train open-source coding models with this data and demonstrate that retry steps yield an improvements of up to 4 and 9 percentage points for overall and challenging execution metrics, respectively, as compared to pre-training without retry data. We showcase that the self-correcting behavior is learned by the model and the increase in downstream accuracy metrics is a result of this additional skill. Finally, we incorporate RetrySQL-trained models into the full text-to-SQL pipeline and showcase that they are competitive in terms of execution accuracy with proprietary models that contain orders of magnitude more parameters.
RetrySQL demonstrates that self-correction can be learned in the text-to-SQL task and provides a novel way of improving generation accuracy for small SQL-oriented language models.

RetrySQL: Text-to-SQL Training with Retry Data for Self-Correcting Query Generation

In this paper, we present Reed-Solomon coded single-stranded representation learning (RSRL), a novel end-to-end model for learning representations for lossless DNA storage of multi-type data.
In contrast to existing learning-based methods, the proposed RSRL is inspired by both error-correction codec and structural biology.
Specifically, RSRL first learns the representations for the subsequent storage from the binary data transformed by the Reed-Solomon codec.
Then, the representations are masked by an RS-code-informed mask to focus on correcting the burst errors occurring in the learning process.
With the decoded representations with error corrections, a novel biologically stabilized loss is formulated to regularize the data representations to possess stable single-stranded structures.
By incorporating these novel strategies, the proposed RSRL can learn highly durable, dense, and lossless representations for the subsequent storage tasks into DNA sequences.
The proposed RSRL has been compared with a number of strong baselines in real-world tasks of multi-type data storage.
The experimental results obtained demonstrate that RSRL can store diverse types of data with much higher information density and durability but much lower error rates.

Learning Structurally Stabilized Representations for Lossless DNA Storage

Recent advancements in video diffusion models have significantly enhanced audio-driven portrait animation. However, current methods still suffer from flickering, identity drift, and poor audio-visual synchronization. These issues primarily stem from entangled appearance-motion representations and unstable inference strategies. In this paper, we introduce **ConsistTalk**, a novel intensity-controllable and temporally consistent talking head generation framework with diffusion noise search inference. First, we propose an **optical flow-guided temporal module (OFT)** that decouples motion features from static appearance by leveraging facial optical flow, thereby reducing visual flicker and improving temporal consistency. Second, we present an **Audio-to-Intensity (A2I) model** obtained through multimodal teacher-student knowledge distillation. By transforming audio and facial velocity features into a frame-wise intensity sequence, the A2I model enables joint modeling of audio and visual motion, resulting in more natural dynamics. This further enables fine-grained, frame-wise control of motion dynamics while maintaining tight audio-visual synchronization. Third, we introduce a **diffusion noise initialization strategy (IC-Init)**. By enforcing explicit constraints on background coherence and motion continuity during inference-time noise search, we achieve better identity preservation and refine motion dynamics compared to the current autoregressive strategy. Extensive experiments demonstrate that ConsistTalk significantly outperforms prior methods in reducing flicker, preserving identity, and delivering temporally stable, high-fidelity talking head videos.

ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search

Recent advancements in diffusion models have made fine-tuning text-to-image models for personalization increasingly accessible, but have also raised significant concerns regarding unauthorized data usage and privacy infringement. Current protection methods are limited to passively degrading image quality, failing to achieve stable control. While Targeted Data Protection (TDP) offers a promising paradigm for active redirection toward user-specified target concepts, existing TDP attempts suffer from poor controllability due to snapshot-matching approaches that fail to account for complete learning dynamics. We introduce TAFAP (Trajectory Alignment via Fine-tuning with Adversarial Perturbations), the first method to successfully achieve effective TDP by controlling the entire training trajectory. Unlike snapshot-based methods whose protective influence is easily diluted as training progresses, TAFAP employs trajectory-matching inspired by dataset distillation to enforce persistent, verifiable transformations throughout fine-tuning. We validate our method through extensive experiments, demonstrating the first successful targeted transformation in diffusion models with simultaneous control over both identity and visual patterns. TAFAP significantly outperforms existing TDP attempts, achieving robust redirection toward target concepts while maintaining high image quality. This work enables verifiable safeguards and provides a new framework for controlling and tracing alterations in diffusion model outputs.

Downloads

Next from AAAI 2026

Breaking Barriers, Finding Boundaries: Not Obviously Manipulable Budget-Feasible Mechanism Design

Similar lecture

Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention

.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

Breaking Barriers, Finding Boundaries: Not Obviously Manipulable Budget-Feasible Mechanism Design

Similar lecture

Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention

Downloads