Singapore

Quantization is critical for efficiently deploying large language models (LLMs). Yet conventional methods remain hardware-agnostic, limited to bit-width constraints, and do not account for intrinsic circuit characteristics such as the timing behaviors and energy profiles of Multiply-Accumulate (MAC) units. This disconnect from circuit-level behavior limits the ability to exploit available timing margins and energy-saving opportunities, reducing the overall efficiency of deployment on modern accelerators. To address these limitations, we propose HALO, a versatile framework for Hardware-Aware Post-Training Quantization (PTQ). Unlike traditional methods, HALO explicitly incorporates detailed hardware characteristics, including critical-path timing and power consumption, into its quantization approach. HALO strategically selects weights with low critical-path-delays enabling higher operational frequencies and dynamic frequency scaling without disrupting the architecture&#39;s dataflow. Remarkably, HALO achieves these improvements with only a few dynamic voltage and frequency scaling (DVFS) adjustments, ensuring simplicity and practicality in deployment. Additionally, by reducing switching activity within the MAC units, HALO effectively lowers energy consumption. Evaluations on accelerators such as Tensor Processing Units (TPUs) and Graphics Processing Units (GPUs) demonstrate that HALO significantly enhances inference efficiency, achieving average performance improvements of 270% and energy savings of 51% over baseline quantization methods, all with minimal impact on accuracy.

AAAI 2026

HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM Acceleration

hardware-aware

llms

quantization

**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.

Quantization is critical for efficiently deploying large language models (LLMs). Yet conventional methods remain hardware-agnostic, limited to bit-width constraints, and do not account for intrinsic circuit characteristics such as the timing behaviors and energy profiles of Multiply-Accumulate (MAC) units. This disconnect from circuit-level behavior limits the ability to exploit available timing margins and energy-saving opportunities, reducing the overall efficiency of deployment on modern accelerators. To address these limitations, we propose HALO, a versatile framework for Hardware-Aware Post-Training Quantization (PTQ). Unlike traditional methods, HALO explicitly incorporates detailed hardware characteristics, including critical-path timing and power consumption, into its quantization approach. HALO strategically selects weights with low critical-path-delays enabling higher operational frequencies and dynamic frequency scaling without disrupting the architecture's dataflow. Remarkably, HALO achieves these improvements with only a few dynamic voltage and frequency scaling (DVFS) adjustments, ensuring simplicity and practicality in deployment. Additionally, by reducing switching activity within the MAC units, HALO effectively lowers energy consumption. Evaluations on accelerators such as Tensor Processing Units (TPUs) and Graphics Processing Units (GPUs) demonstrate that HALO significantly enhances inference efficiency, achieving average performance improvements of 270% and energy savings of 51% over baseline quantization methods, all with minimal impact on accuracy.

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.

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.

Conversational AI agents are envisioned to provide social
support or functional service to human users via natural
language interactions. The popularity of conversational AI
has grown unprecedentedly with the advent of ChatGPT, which
showcases exceptional proficiency in the capabilities of
context understanding and response generation with large
language models (LLMs). However, typical conversational
systems are built to follow instructions, which means that
the conversation is led by the user, and the system simply
follows the user’s instructions or intents. My research
endows the conversational AI with the capabilities of
creating or controlling the conversation to achieve the
conversational goals by taking initiative and anticipating
impacts on themselves or human users, namely Proactive
Conversational AI. I will also highlight the importance of
moving towards building human-centered proactive
conversational AI that emphasize human needs and
expectations, and that considers ethical and social
implications of these agents, rather than solely focusing
on technological capabilities.

Towards Human-centered Proactive Conversational AI

Understanding opinion evolution in complex social networks is crucial for modeling social influence and predicting collective behavior. Yet, most models overlook how community structures shape opinion updates, often assuming homogeneous influence. This abstraction neglects individuals’ stronger responsiveness to intra-community peers—an empirically observed driver of localized consensus and inter-group polarization. We propose GCAOFP, a co-evolutionary framework that jointly models opinion dynamics and community formation as an integrated process. In GCAOFP, agents strategically alternate between two coupled modules: (1) a Community Dynamics Module, where agents play a non-cooperative game to optimize community memberships based on opinion alignment and structural cohesion; and (2) an Opinion Adjustment Module, where agents revise opinions via a bounded-confidence mechanism modulated by community-induced influence weights. This dual-stage process captures the feedback loop between structure and opinion. We prove that GCAOFP converges to stable equilibria, ensuring intra-community consensus and inter-community diversity—dynamics that standard models fail to replicate. Experiments on real-world networks show that GCAOFP better reproduces localized opinion clusters, while offering strong scalability and interpretability, illuminating the strategic foundations of polarization.

Game Theory Based Community-Aware Opinion Dynamics

As artificial intelligence (AI) becomes increasingly prevalent in society, there is a critical need for accessible K-12 educational resources that introduce students to AI and robotics concepts through engaging, hands-on experiences. In this paper, we present a scalable workshop framework that uses narrative-driven problem solving to teach fundamental AI and autonomous systems concepts to students in grades 5-12. Developed through a collaboration between AI researchers and education specialists, Bot Blitz employs Sphero RVR+ robots within immersive storylines ranging from fairground rescue missions for younger students to urban traffic management scenarios for high schoolers. Preliminary observations from workshops with 56 students show high engagement levels and successful completion of programming challenges.

Bot Blitz: A Scalable Hands-On Workshop for Teaching AI and Robotics Concepts Through Narrative-Driven Problem Solving

Hierarchical data pervades diverse machine learning applications, including natural language processing, computer vision, and social network analysis. Hyperbolic space, characterized by its negative curvature, has demonstrated strong potential in such tasks due to its capacity to embed hierarchical structures with minimal distortion. Previous evidence indicates that the hyperbolic representation capacity can be further enhanced through kernel methods. However, existing hyperbolic kernels still suffer from mild geometric distortion or lack adaptability. This paper addresses these issues by introducing a curvature-aware de Branges–Rovnyak space, a reproducing kernel Hilbert space (RKHS) that is isometric to a Poincar$\'$e ball. We design an adjustable multiplier to select the appropriate RKHS corresponding to the hyperbolic space with any curvature adaptively. Building on this foundation, we further construct a family of adaptive hyperbolic kernels, including the novel adaptive hyperbolic radial kernel, whose learnable parameters modulate hyperbolic features in a task-aware manner. Extensive experiments on visual and language benchmarks demonstrate that our proposed kernels outperform existing hyperbolic kernels in modeling hierarchical dependencies.

Adaptive Hyperbolic Kernels: Modulated Embedding in de Branges-Rovnyak Spaces

We propose an extension of Description Logics (DLs) with generic concepts
and conditional axioms. Inspired by object-oriented languages, generic
concepts allow a compact definition of concepts with similar structures.
For example, one can define a generic concept Owner[X] to describe objects
that own another object from X, and later use a specific replacement of the
parameter X, such as Owner[Pet] representing pet owners. Conditional axioms
can be used to set bounds on the values that replace the generic parameters.
For example, we could restrict replacements of X in a concept Keeper[X] to
only subconcepts of Pet. As the set of possible parameter replacements can
be infinite and even uncountable, the generic extensions are, in general,
undecidable. To identify decidable generic DLs, we focus on the case of
terminologies, requiring that variables are only used in definitions of
generic concepts. We formulate restrictions that allow a reduction
of generic entailment to classical entailment and further conditions that
ensure decidability.

Extending Description Logics with Generic Concepts – the Case of Terminologies

In semi-decentralized federated learning, devices primarily rely on device-to-device communication but occasionally interact with a central server. Periodically, a sampled subset of devices uploads their local models to the server, which computes an aggregate model. The server can then either (i) share this aggregate model only with the sampled clients (sampled-to-sampled, S2S) or (ii) broadcast it to all clients (sampled-to-all, S2A). Despite their practical significance, a rigorous theoretical and empirical comparison of these two strategies remains absent.
We address this gap by analyzing S2S and S2A within a unified convergence framework that accounts for key system parameters: sampling rate, server aggregation frequency, and network connectivity. Our results---both analytical and experimental---reveal distinct regimes where one strategy outperforms the other, depending primarily on the degree of data heterogeneity across devices. These insights lead to concrete design guidelines for practical semi-decentralized FL deployments.

A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication

Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and object transformations, and tend to show weak adherence to complex instructions. We address these limitations by introducing Reason-3D, a text-to-scene model powered by large reasoning models (LRMs). Reason-3D integrates object retrieval using captions covering physical, functional, and contextual attributes. Reason-3D then places the selected objects based on implicit and explicit layout constraints, and refines their positions with collision-aware spatial reasoning. Evaluated on instructions ranging from simple to complex indoor configurations, Reason-3D significantly outperforms previous methods in human-rated visual fidelity, adherence to constraints, and asset retrieval quality. Beyond its contribution to the field of text-to-scene generation, our work showcases the advanced spatial reasoning abilities of modern LRMs. Additionally, we release the codebase to further the research in object retrieval and placement with LRMs.

Text-to-Scene with Large Reasoning Models

Probabilistic Circuits (PCs) are a class of generative models that allow exact and tractable inference for diverse queries. While recent developments have enabled the learning of deep and expressive PCs, this increased capacity can often lead to overfitting, especially when data is limited. In this work, we analyze PC overfitting from a log-likelihood-landscape perspective and show that it is often caused by convergence to $\textit{sharp optima}$ that generalize poorly. Inspired by sharpness aware minimization in neural networks, we propose a Hessian-based regularizer for training PCs. As a key contribution, we show that the trace of the Hessian of the log-likelihood—a sharpness proxy that is typically intractable in deep neural networks- can be computed efficiently for PCs. Minimizing this Hessian trace induces a natural gradient-norm-based regularizer that yields simple closed-form parameter updates for EM, and integrates seamlessly with gradient based methods. Experiments on synthetic and real-world PC benchmarks demonstrate that our method consistently guides PCs toward flatter minima, improving generalization over standard training.

Tractable Sharpness-Aware Learning of Probabilistic Circuits

Identity-preserving models have led to notable progress in generating personalized content. Unfortunately, such models also exacerbate risks when misused, for instance, by generating threatening content targeting specific individuals. This paper introduces the Attribute Misbinding Attack, a novel method that poses a threat to identity-preserving models by inducing them to produce Not-Safe-For-Work (NSFW) content. The attack's core idea involves crafting benign-looking textual prompts to circumvent text-filter safeguards and leverage a key model vulnerability: flawed attribute binding that stems from its internal attention bias. This results in misattributing harmful descriptions to a target identity and generating NSFW outputs. To facilitate the study of this attack, we present the Misbinding Prompt evaluation set, which examines the content generation risks of current state-of-the-art identity-preserving models across four risk dimensions: pornography, violence, discrimination, and illegality. Additionally, we introduce the Attribute Binding Safety Score (ABSS), a metric for concurrently assessing both content fidelity and safety compliance. Experimental results show that our Misbinding Prompt evaluation set achieves a 5.28 \% higher success rate in bypassing five leading text filters (including GPT-4o) compared to existing main-stream evaluation sets, while also demonstrating the highest proportion of NSFW content generation. The proposed ABSS metric enables a more comprehensive evaluation of identity-preserving models by concurrently assessing both content fidelity and safety compliance. The dataset and code will be open-sourced. For further experimental data and anonymous open-source links, please see the appendix.

Disclaimer: This paper contains NSFW imagery that might be offensive to some readers.

Unveiling the Attribute Misbinding Threat in Identity-Preserving Models

Scaling deep learning to massive and diverse internet data has driven remarkable breakthroughs in domains such as video generation and natural language processing.
Robot learning, however, has thus far failed to replicate this success and remains constrained by a scarcity of available data.
Learning from Videos (LfV) methods aim to address this data bottleneck by augmenting traditional robot data with large-scale internet video.
This video data provides foundational information regarding physical dynamics, behaviours, and tasks, and can be highly informative for general-purpose robots.

This survey systematically examines the emerging field of LfV.
We first outline essential concepts, including detailing fundamental LfV challenges such as distribution shift and missing action labels in video data.
Next, we comprehensively review current methods for extracting knowledge from large-scale internet video, overcoming LfV challenges, and improving robot learning through video-informed training.
The survey concludes with a critical discussion of future opportunities.
Here, we emphasize the need for scalable foundation model approaches that can leverage the full range of available internet video and enhance the learning of robot policies and dynamics models.
Overall, the survey aims to inform and catalyse future LfV research, driving progress towards general-purpose robots.

Downloads

Next from AAAI 2026

Towards Human-centered Proactive Conversational AI

Similar lecture

Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization