Singapore

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guided by a novel performance reward. Based on this framework, we take a deeper dive into the code efficiency problem, identifying then proposing methods to overcome key bottlenecks: (1) Dynamic exploration overcomes the static data constraints of offline fine-tuning, enabling the discovery of more efficient code implementations. (2) The error-insensitive reinforcement learning method and high-contrast efficiency signals are crucial for mitigating systematic errors and achieving effective optimization. (3) Online exploration is most effective when starting from a high-correctness baseline, as this allows for efficiency improvements without sacrificing accuracy. With these discoveries, we finally propose a two-stage tuning method, which achieves high and balanced performance across correctness and efficiency. The results of experiments show the effectiveness of the method, which improves code correctness by 10.18\% and runtime efficiency by 7.75\% on a 7B model, achieving performance comparable to much larger model.

AAAI 2026

Towards Better Correctness and Efficiency in Code Generation

nlp: code generation / program synthesis from natural language

nlp: (large) language models

nlp: generation

## 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.

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.

We study active mitigation of selection bias in statistical learning. That is sequential maximization over a set $\mathcal{A}$ of the expectation of a reward function $R(a,X)$ w.r.t. a r.v. $X$ drawn from a target distribution $P_T$ possibly different from the (supposedly dominating) source distribution $P_S$ under which rewards are observed. The importance function $dP_T/dP_S(x)$ with which the sequentially observed biased rewards should be ideally weighted being unknown in practice, auxiliary information is assumed to be available in the form of known moments of the target distribution $P_T$ for debiasing purposes. In the batch setting, this problem has already been studied and can be solved under certain conditions in two successive steps: 1) identify a weight function so as to approximate the moments 2) maximize the resulting (empirical version of the) weighted reward. In the active setting, if the problem boils down to identifying the best arm in a stochastic multi-armed bandit (MAB) model, the presence of selection bias strongly affects the complexity of the sequential optimization problem and requires the development of a new algorithmic approach, as we show here. In a fixed confidence setting, we introduce a novel notion of complexity, which accounts for the balance between arm evaluation and (parametric) weight function estimation, establish lower bounds and propose an algorithm proved to be near optimal. Theoretical guarantees are backed up by numerical results.

Best Arm Identification with Biased Contexts

Large language models (LLMs) show significant improvement in code generation. A common practice is sampling multiple candidate codes to increase the likelihood of producing an accurate solution. However, effectively identifying the best candidate from the pool is a significant challenge. Although existing code consensus methods attempt to solve this issue, they suffer from a critical problem: relying on test cases generated by LLMs, which can be flawed or provide incomplete coverage. This problem can result in erroneous validations, causing correct code to fail flawed tests and preventing the detection of functional differences in candidate code solutions. To address these issues, we present the Dynamic-Static Synergistic Selection Method, a novel framework that combines two complementary analytical approaches. First, it uses the abstract syntax tree (AST) to detect and filter candidate solutions and test cases. Second, the method statically analyzes the solutions' quality, then dynamically validates functional consistency based on execution results of extracted inputs, which neutralizes the impact of faulty tests. Extensive experiments demonstrate that this synergistic approach significantly outperforms existing methods, substantially enhancing the correctness of the selected code.

Dynamic-Static Synergistic Selection Method for Candidate Code Solutions with Generated Test Cases

Synthetic aperture radar (SAR) image acquisition incurs high costs, motivating SAR image generation research under limited data. However, SAR's inherent azimuth sensitivity complicates this task, where target scattering characteristics vary significantly with azimuth angle, leading to azimuth-target coupling and azimuth overfitting under data scarcity. Most existing methods require supplementary data to work effectively, limiting their practicality. In this paper, we propose SAR-DisentDM, a novel semantic-disentangled diffusion model for limited-data SAR image generation, without requiring any auxiliary resources. We develop a physics-aware diffusion architecture that explicitly models semantic knowledge of SAR images, including intrinsic characteristics, contextual diversity, and measurement randomness. A key innovation is the attention-guided semantic disentanglement module (AGSD), designed to decouple category-specific features from azimuth-variable scattering patterns using dual disentangled losses with time-step-adaptive optimization. To further avoid azimuth overfitting, we introduce azimuth angle perturbation augmentation mechanism (AAPA) to enhance azimuth angle diversity. Extensive evaluations validate that SAR-DisentDM enables controllable SAR image synthesis with designated attributes, significantly improving representation and generalization abilities under limited data. Synthetic imagery from our approach boosts automatic target recognition (ATR) accuracy beyond state-of-the-art methods.

SAR-DisentDM: A Semantic-Disentangled Diffusion Model for Limited-Data SAR Image Synthesis

Monocular 3D object detection is a cost-effective solution for applications like autonomous driving and robotics, but remains fundamentally ill-posed due to inherently ambiguous depth cues. Recent DETR-based methods attempt to mitigate this through global attention and auxiliary depth prediction, yet they still struggle with inaccurate depth estimates. Moreover, these methods often overlook instance-level detection difficulty, such as occlusion, distance, and truncation, leading to suboptimal detection performance. We propose MonoDLGD, a novel Difficulty-Aware Label-Guided Denoising framework that adaptively perturbs and reconstructs ground-truth labels based on detection uncertainty. Specifically, MonoDLGD applies stronger perturbations to easier instances and weaker ones into harder cases, and then reconstructs them to effectively provide explicit geometric supervision. By jointly optimizing label reconstruction and 3D object detection, MonoDLGD encourages geometry-aware representation learning and improves robustness to varying levels of object complexity. Extensive experiments on the KITTI benchmark demonstrate that MonoDLGD achieves state-of-the-art performance across all difficulty levels.

Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection

Autonomous aerial robots must operate in cluttered, wind-
disturbed environments where turbulence and gusts generated
by wind-object and terrain interactions introduce significant aerodynamic risks, including orientation instability, sensor degradation, control drift, and increased power consumption, often leading to mission failure or crash. We present Graphlets-based Zero-Shot Planning Framework (GZS), a novel, non-parametric, fast computation, memory-efficient,
zero-shot training-free onboard inference framework for real-time 3D spatial-aware aerodynamic risk perception that operates without prior scene knowledge. GZS dynamically classifies point clouds to extract local topology, incorporates physics-informed modeling of wind interactions, and applies attention-guided segment matching to generate onboard 3D representations of wind-induced aerodynamic risk. It transforms unstructured scene segments into structured graphlets topologies encoding aerodynamic risk-aware features, enabling UAVs to identify and navigate through regions of minimal aerodynamic hazard in real time and without prior training in any environment. Unlike computational fluid dynamics(CFD)-based, deep learning, or map-dependent approaches, GZS performs zero-shot aerodynamic risk estimation in previously unseen and dynamic conditions. Extensive experiments demonstrate 90-95% accurate aerodynamic risk zone identification compared to conventional methods of CFDs and wind tunnels, while substantially reducing computational and memory overhead, and a 100% success rate in creating onboard 3d spatial-aware risk perceptions. Our results establish GZS as a framework for a zero-shot, non-parametric, robust, aerodynamic risk perception for autonomous real-time trajectory planning in wind-affected aerial environments.

Real-Time Path Planning for UAVs in Windy Environments Without Computational Fluid Dynamics

Spiking Large Language Models (LLMs) have emerged as an energy-efficient alternative to conventional LLMs through their event-driven computation. To effectively obtain spiking LLMs, researchers develop different ANN-to-SNN conversion methods by leveraging pre-trained ANN parameters while inheriting the energy efficiency of SNN. However, existing conversion methods struggle with extreme activation outliers and incompatible nonlinear operations of ANN-based LLMs. To address this, we propose a loss-less ANN-SNN conversion for fully spike-driven LLMs, termed LAS. Specifically, LAS introduces two novel neurons to convert the activation outlier and nonlinear operation of ANN-based LLMs. Moreover, LAS tailors the spike-equivalent Transformer components for spiking LLMs, which can ensure full spiking conversion without any loss of performance. Experimental results on six language models and two vision-language models demonstrate that LAS achieves loss-less conversion. Notably, on OPT-66B, LAS even improves the accuracy of 2% on the WSC task. In addition, the parameter and ablation studies further verify the effectiveness of LAS. Code is available at https://github.com/lc783/LAS.

LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models

Knowledge graphs (KGs) play a vital role in intelligent education by offering structured representations of educational content. However, constructing multimodal educational knowledge graphs (EKGs) from diverse open educational resources remains a challenge due to the reliance on costly manual annotations and the lack of multimodal integration. In this work, we propose an automated framework that harnesses the reasoning capabilities of large language models (LLMs) to construct multimodal EKGs from open courses efficiently. In our framework, an Extraction-Verification-Integration-Augmentation pipeline is designed to incrementally extract and refine disciplinary concepts from learning resources. Texts, images, videos and audios are aligned with their corresponding concepts. To ensure semantic consistency across modalities, we propose a cross-modal alignment method based on shared structural and semantic features. Using our framework, we build SciMKG, a large-scale multimodal EKG for Chinese K12 education in sciences (biology, physics, and chemistry), encompassing 1,356 knowledge points, 34,630 multimodal concepts, and 191,928 relational triples. Experimental results show that our method improves concept extraction F1 score by 9\% over state-of-the-art baselines; both automatic and human evaluations confirm the robustness of our multimodal alignment method. SciMKG and our construction toolkit will be publicly released to support further research and applications in AI-driven education.

SciMKG: A Multimodal Knowledge Graph for Science Education with Text, Image, Video and Audio

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of the smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher models often reflect only surface-level traces of their underlying authentic reasoning. Insights from cognitive neuroscience suggest that authentic reasoning involves a complex interweaving between meta-reasoning—which selects the appropriate sub-problem from multiple candidates—and solving, which addresses the sub-problem. It means that authentic reasoning has implicit multi-branch structure. Supervised fine-tuning collapses this rich structure into a flat sequence of token prediction in teacher's reasoning path, which cannot distill this structure to student. To address this limitation, we propose RLKD, a reinforcement learning (RL)-based distillation framework guided by a novel Generative Structure Reward Model (GSRM). Our GSRM converts the reasoning path into multiple meta-reasoning-solving steps and gives the reward to measure the alignment between the reasoning structures of student and teacher. Our RLKD combines this reward with RL, enables the student LLM to internalize the teacher’s implicit multi-branch structure in authentic reasoning, rather than merely mimicking fixed teacher's output paths. Experiments show that RLKD, even when trained on only 0.1% of the data under an RL-only regime, surpasses the performance of standard SFT-RL pipelines and further unleashes the potential reasoning ability of the student LLM than SFT-based distillation. Code is in supplemental material and will be released after review.

RLKD: Distilling LLMs’ Reasoning via Reinforcement Learning

Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have introduced a retrieval mechanism that retrieves query-relevant KV caches for question answering, enhancing the efficiency and accuracy of long real-world videos. However, the compression and retrieval of KV caches are still not fully explored. In this paper, we propose \textbf{StreamKV}, a training-free framework that seamlessly equips Video-LLMs with advanced KV cache retrieval and compression. Compared to previous methods that used uniform partitioning, StreamKV dynamically partitions video streams into semantic segments, which better preserves semantic information. For KV cache retrieval, StreamKV calculates a summary vector for each segment to retain segment-level information essential for retrieval. For KV cache compression, StreamKV introduces a guidance prompt designed to capture the key semantic elements within each segment, ensuring only the most informative KV caches are retained for answering questions. Moreover, StreamKV unifies KV cache retrieval and compression within a single module, performing both in a layer-adaptive manner, thereby further improving the effectiveness of streaming video question answering. Extensive experiments on public StreamingVQA benchmarks demonstrate that StreamKV significantly outperforms existing Online Video-LLMs, achieving superior accuracy while substantially improving both memory efficiency and computational latency. The code will be released.

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression

Predicting spatiotemporal fields governed by partial differential equations (PDEs) from sparse sensor data is a critical and long-standing challenge in science and engineering. Recent deep learning approaches, particularly neural operators, have shown considerable promise in solving PDEs. However, their performance degrades significantly in the demanding regime of extreme sparsity, characterized by spatial sensor coverage of less than 1% and limited temporal observations. To overcome this limitation, we propose a novel framework that decouples the task into two stages: spatial reconstruction and temporal extrapolation. In the first stage, rather than reconstructing the high-dimensional physical field directly, our model learns to reconstruct the complete latent features from sparse observations—features that would otherwise be extracted from a dense field. This process is stabilized by a Vector Quantization (VQ) bottleneck, which discretizes the latent space. In the second stage, a decoder-only Transformer performs temporal extrapolation by autoregressively predicting the future sequence of these discrete latent indices. This design inherently allows the model to generalize to new initial conditions and varying forecast horizons, akin to standard autoregressive models. We validate our framework on three challenging benchmarks, achieving state-of-the-art (SOTA) performance under severe sparsity constraints. Furthermore, we introduce a challenging benchmark dataset based on fire dynamics simulations. On this benchmark, our model successfully forecasts the field's evolution 30 frames into the future from a single timeframe with less than 0.1% spatial observations—a result that pushes well beyond the capabilities of existing methods.

Content not yet available

Next from AAAI 2026

Best Arm Identification with Biased Contexts

Similar lecture

ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?