Singapore

Large language models have revolutionized textual reasoning, yet their ability to act meaningfully in multimodal, real-world environments remains limited. They struggle to ground their decisions in visual context, adapt to changing goals, and plan actions over time—shortcomings that stem from a lack of structured, goal-driven reasoning and insufficient representations of the physical world.

In this talk, I present a unified framework for building embodied agents that can see, simulate, and reason. I begin by introducing methods for learning world simulators from data, arguing that visual reasoning—like textual reasoning—benefits from step-by-step processing. Inverting a physics simulator becomes key: agents must infer structured 3D neural representations of objects, parts, motions, and scenes directly from raw video. I describe methods for extracting such representations using generative priors, injecting them into vision-language models (VLMs), and scaling up their supervision via generative 3D simulation and fast, modular physics engines. These simulators enable agents to anchor their predictions in grounded physical reality, reducing hallucinations and improving control.

Complementing this simulation capability, I explore techniques that enable agents to reason over time and adapt their behavior. By integrating structured memory systems, agents learn to retain and retrieve relevant experiences to inform long-horizon plans. Language-based reflective feedback allows them to refine their strategies beyond what sparse rewards offer, forming abstractions that generalize across tasks. When trained to ground their reasoning directly in the visual environment, agents gain the ability to set subgoals, explore effectively, and verify their own hypotheses.

Together, these advances point toward autonomous systems that simulate before they act, reflect after they fail, and maintain an ongoing awareness of goals, constraints, and context. I will illustrate these capabilities across web automation, robotics, and interactive assistance, showing how agents that see, simulate, and reason offer a promising path toward general-purpose embodied intelligence.

AAAI 2026

Towards Embodied Agents that See, Simulate, and Reason

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

invited talk

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.

Our world is constantly evolving, and human beings
continuously enhance their knowledge by learning from their
experiences throughout life. Despite significant
advancements in embodied AI, current agents struggle to
operate reliably, robustly, and continually in complex,
real-world multimodal environments due to complex problems
that span large and diverse domains, especially when faced
with out-of-distribution (OOD) scenarios they have not
previously encountered. Our goal is to develop a
multimodal, embodied AI system that continually enhances
its capabilities and skills through safe and robust
interactions with an ever-changing, multimodal world. This
is enabled by a novel, adaptively expandable memory
architecture that integrates both long- and short-term
information across multiple modalities. The system
selectively decides what to store and learn, filtering out
adversarial or low-quality inputs to prevent negative
transfer and distractions, while improving overall
efficiency and effectiveness.

Towards Continually-Evolving Multimodal Embodied AI: Selective and Expandable Multimodal Memory System

Rice cultivation supplies half the world's population with staple food, while also being a major driver of freshwater depletion—consuming roughly a quarter of global freshwater—and accounting for $\sim$48\% of greenhouse gas emissions from croplands. In regions like Punjab, India, where groundwater levels are plummeting at 41.6 cm/year, adopting water-saving rice farming practices is critical. Direct-Seeded Rice (DSR) and Alternate Wetting and Drying (AWD) can cut irrigation water use by 20–40\% without hurting yields, yet lack of spatial data on adoption impedes effective adaptation policy and climate action. We present a machine learning framework to bridge this data gap by monitoring sustainable rice farming at scale. In collaboration with agronomy experts and a large-scale farmer training program, we obtained ground-truth data from $\sim$1,400 fields across Punjab. Leveraging this partnership, we developed a novel dimensional classification approach that decouples sowing and irrigation practices, achieving F1 scores of 0.772 and 0.806 respectively, solely employing Sentinel-1 satellite imagery. Explainability analysis reveals that DSR classification is reliable while AWD classification depends primarily on planting schedule differences, as Sentinel-1's 12-day revisit frequency cannot capture the higher frequency irrigation cycles characteristic of AWD practices. Applying this model across 3 million fields reveals spatial inequities in adoption at the state level, highlighting gaps and opportunities for policy targeting. Our district-level adoption rates correlate strongly (Pearson=0.87) with government estimates. This study provides policymakers and sustainability programs a powerful tool to track practice adoption, inform targeted interventions, and drive data-driven policies for water conservation and climate mitigation at regional scale. We release all code and models at: \url{https://github.com/anonymous-repo} to support reproducibility and future research.

Machine Learning for Sustainable Rice Production: Region-Scale Monitoring of Water-Saving Practices in Punjab, India

As AI technologies grow more influential in shaping modern
life, there is an urgent need to make AI literacy
accessible beyond academic and technical communities. This
paper presents the design, delivery, and evaluation of an
online AI course targeting the general public. The course
combined asynchronous lectures, interactive live sessions,
and reflective assignments. Of the 343 people who
registered, 169 completed the program. Using validated
instruments administered before and after the course, we
measured changes in participants’ attitudes toward AI and
their AI literacy. Our findings revealed statistically
significant changes in AI literacy, specifically in
awareness, usage, and evaluation constructs, as well as a
rise in positive attitudes toward AI. High satisfaction
scores and qualitative feedback further support the
course’s effectiveness. These findings reinforce the
importance of inclusive, scalable educational interventions
for empowering the public to navigate AI technologies.

Educating the Public in Artificial Intelligence: Insights from a Large-Scale Course

Blind Image Quality Assessment plays a key role in vision tasks, yet existing models often fail to effectively capture subtle distortion cues, leading to a misalignment with human subjective judgments. We identify that the root cause of this limitation lies in the lack of reliable distortion priors, as methods typically learn shallow relationships between unified image features and quality scores, resulting in their insensitive nature to distortions and thus limiting their performance. To address this, we introduce DR.Experts, a novel prior-driven BIQA framework designed to explicitly incorporate distortion priors, enabling a reliable quality assessment. DR.Experts begins by leveraging a degradation-aware vision-language model to obtain distortion-specific priors, which are further refined and enhanced by the proposed Distortion-Saliency Differential Module through distinguishing them from semantic attentions, thereby ensuring the genuine representations of distortions. The refined priors, along with semantics and bridging representation, are then fused by a proposed mixture-of-experts style module named the Dynamic Distortion Weighting Module. This mechanism dynamically weights each distortion-specific feature as per its perceptual impact, ensuring that the final quality prediction aligns with human perception. Extensive experiments conducted on five challenging BIQA benchmarks demonstrate the superiority of DR.Experts over current methods and showcase its excellence in terms of generalization and data efficiency. Code and checkpoints will be available upon publication.

DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment

Rain degrades the visual quality of multi-view images, which are essential for 3D scene reconstruction, resulting in inaccurate and incomplete reconstruction results. Existing datasets often overlook two critical characteristics of real rainy 3D scenes: the viewpoint-dependent variation in the appearance of rain streaks caused by their projection onto 2D images, and the reduction in ambient brightness resulting from cloud coverage during rainfall. To improve data realism, we construct a new dataset named OmniRain3D that incorporates perspective heterogeneity and brightness dynamicity, enabling more faithful simulation of rain degradation in 3D scenes. Based on this dataset, we propose an end-to-end reconstruction framework named REVR-GSNet (Rain Elimination and Visibility Recovery for 3D Gaussian Splatting). Specifically, REVR-GSNet integrates recursive brightness enhancement, Gaussian primitive optimization, and GS-guided rain elimination into a unified architecture through joint alternating optimization, achieving high-fidelity reconstruction of clean 3D scenes from rain-degraded inputs. Extensive experiments show the effectiveness of our dataset and method. Our dataset and method provide a foundation for future research on multi-view image deraining and rainy 3D scene reconstruction. Both the dataset and code will be publicly available.

Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning

Accurate conversion rate (CVR) prediction is critical for recommender systems to capture user conversion intent and increase platform revenues. Traditional CVR models commonly suffer from sample selection bias (SSB) and data sparsity (DS), which has led to the adoption of click-through & conversion rate (CTCVR) multi-task learning frameworks to alleviate these issues. However, existing methods implicitly mislabel some unclicked samples with genuine conversion potential as negatives, thereby exacerbating the false negative sample (FNS) problem. To address this, we propose IdeFN, a multi‑task CVR framework that identifies false negatives in the unclicked space to enable CVR prediction across the entire exposure space and leverages CTR as an auxiliary task for shared‑parameter learning. Specifically, IdeFN consists of two main components, i.e., relaxed partial optimal transport (RPOT) module and sample relabeling mechanism (SRM). The former estimates the soft matching strengths between unclicked samples and positive samples under a relaxed partial optimal transport formulation, establishing corresponding relationships between these samples. The latter adaptively re-labels the unclicked samples according to the derived matching strengths, without relying on static or heuristic thresholds, thus enhancing the reliability of the generated pseudo-labels. Experimental results demonstrate that IdeFN effectively mitigates the FNS problem, achieving substantial improvements in CVR prediction accuracy.

IdeFN: Identifying Unclicked Space False Negatives via Relaxed Partial Optimal Transport for Conversion Rate Prediction

Existing speech tokenizers typically assign a fixed number of tokens per second, regardless of the varying information density or temporal fluctuations in the speech signal. This uniform token allocation mismatches the intrinsic structure of speech, where information is distributed unevenly over time. To address this, we propose VARSTok, a VAriable-frame-Rate Speech Tokenizer that adapts token allocation based on local feature similarity. VARSTok introduces two key innovations: (1) a temporal-aware density peak clustering algorithm that adaptively segments speech into variable-length units, and (2) a novel implicit duration coding scheme that embeds both content and temporal span into a single token index, eliminating the need for auxiliary duration predictors. Extensive experiments show that VARSTok significantly outperforms strong fixed-rate baselines. Notably, it achieves superior reconstruction naturalness while using up to 23% fewer tokens than a 40 Hz fixed-frame-rate baseline. VARSTok further yields lower word error rates and improved naturalness in zero-shot text-to-speech synthesis. To the best of our knowledge, this is the first work to demonstrate that a fully dynamic, variable-frame-rate acoustic speech tokenizer can be seamlessly integrated into downstream speech language models.

Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding

Multi-view clustering of remote sensing data plays a vital role in Earth observation analysis. Recently, deep graph clustering methods based on contrastive learning have significantly improved feature representation capabilities. However, most existing approaches treat all views equally, neglecting the inherent uniqueness and heterogeneity across views, which often results in two major issues: 1) discriminative features from clustering-friendly views are underexplored; and 2) redundant or noisy information from less informative views can degrade the shared representation. To address these challenges, we propose a novel multi-view graph clustering framework termed CF-MVGC for remote sensing data, which dynamically preserves discriminative features and suppresses redundancy by assessing view affinity. Specifically, we employ a dual-stage representation learning strategy to extract both view-specific discriminative features and cross-view consistent representations. To further exploit and adaptively integrate complementary information across views, we design a progressive feature filtering model that dynamically evaluates view affinity using two novel metrics, i.e., view fidelity index (VFI) and view criticality index (VCI). Based on these assessments, the module adaptively modulates feature update and reset signals, reinforcing informative views while suppressing noisy or redundant ones. Views with high affinity receive strengthened update signals to retain valuable features, while those with low affinity are subjected to enhanced reset operations to eliminate noise and redundancy. The resulting high-quality, discriminative representations lead to improved clustering performance, establishing a positive feedback loop. Experimental results on four benchmark datasets demonstrate the effectiveness and superiority of CF-MVGC against its competitors.

Cross-View Progressive Feature Filtering for Multi-View Graph Clustering in Remote Sensing

AI and Program Reviewing Panel

Over the past few years, Artificial Intelligence has bounded into the mainstream of society.  Remarkable technical achievements in the use of Deep Learning and  Large Language Models have given rise to expectations and hype regarding the possibility of achieving artificial general intelligence, as well as general concerns over the potential deleterious consequences of emerging AI technologies and how to ensure their responsible use. In this panel we engage four Past AAAI Presidents to discuss their views on questions relating to the current state and future of AI research, including such topics as important emerging application areas, current technical challenges, the eventual prospects for achieving artificial general intelligence, and potential AI risks and solutions.

Downloads

Next from AAAI 2026

Towards Continually-Evolving Multimodal Embodied AI: Selective and Expandable Multimodal Memory System

Similar lecture

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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

Towards Continually-Evolving Multimodal Embodied AI: Selective and Expandable Multimodal Memory System

Similar lecture

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads