Irwin King
YOU?
Author Swipe
View article: PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction Open
Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an artificial ordering on inherently unordered point sets, forcin…
View article: RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback Open
Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the iterati…
View article: From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents
From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents Open
Retrieval-augmented generation agents development is hindered by the lack of process-level supervision to effectively guide agentic capabilities like task decomposition, retriever invocation, and stepwise decision-making. While reinforceme…
View article: A phenomenographic approach to students’ conceptions of learning artificial intelligence (AI) in secondary schools
A phenomenographic approach to students’ conceptions of learning artificial intelligence (AI) in secondary schools Open
AI education for K-12 students is an emerging necessity, and considering students’ perspectives when developing effective AI education curricula in K-12 settings is essential. Few studies investigated secondary students’ conceptions of lea…
View article: Implicit Reasoning in Large Language Models: A Comprehensive Survey
Implicit Reasoning in Large Language Models: A Comprehensive Survey Open
Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies ha…
View article: Think Before You Talk: Enhancing Meaningful Dialogue Generation in Full-Duplex Speech Language Models with Planning-Inspired Text Guidance
Think Before You Talk: Enhancing Meaningful Dialogue Generation in Full-Duplex Speech Language Models with Planning-Inspired Text Guidance Open
Full-Duplex Speech Language Models (FD-SLMs) are specialized foundation models designed to enable natural, real-time spoken interactions by modeling complex conversational dynamics such as interruptions, backchannels, and overlapping speec…
View article: Track and Tweak: Monitoring and Improving Group Fairness for Temporal Graph Neural Networks in Real Time
Track and Tweak: Monitoring and Improving Group Fairness for Temporal Graph Neural Networks in Real Time Open
The prevalence of temporal networks in real-world applications, like financial transaction networks for loan approval prediction, poses significant challenges for ensuring fairness across different groups. These dynamic systems increasingl…
View article: Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning
Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning Open
Federated Unsupervised Learning (FUL) aims to learn expressive representations in federated and self-supervised settings. The quality of representations learned in FUL is usually determined by uniformity, a measure of how uniformly represe…
View article: From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents Open
Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex, multi…
View article: Towards Geometry Problem Solving in the Large Model Era: A Survey
Towards Geometry Problem Solving in the Large Model Era: A Survey Open
Geometry problem solving (GPS) represents a critical frontier in artificial intelligence, with profound applications in education, computer-aided design, and computational graphics. Despite its significance, automating GPS remains challeng…
View article: Learning Binarized Representations with Pseudo-positive Sample Enhancement for Efficient Graph Collaborative Filtering
Learning Binarized Representations with Pseudo-positive Sample Enhancement for Efficient Graph Collaborative Filtering Open
Learning vectorized embeddings is fundamental to many recommender systems for user-item matching. To enable efficient online inference, representation binarization, which embeds latent features into compact binary sequences, has recently s…
View article: NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction Open
Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several …
View article: Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation
Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation Open
Graph neural networks (GNNs), which capture graph structures via a feature aggregation mechanism following the graph embedding framework, have demonstrated a powerful ability to support various tasks. According to the topology properties (…
View article: WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback Open
Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment. In this paper, we identify key reasoning skills essential…
View article: Beyond Linearity: Squeeze-and-Recalibrate Blocks for Few-Shot Whole Slide Image Classification
Beyond Linearity: Squeeze-and-Recalibrate Blocks for Few-Shot Whole Slide Image Classification Open
Deep learning has advanced computational pathology but expert annotations remain scarce. Few-shot learning mitigates annotation burdens yet suffers from overfitting and discriminative feature mischaracterization. In addition, the current f…
View article: G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation
G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation Open
Explainable recommendation has demonstrated significant advantages in informing users about the logic behind recommendations, thereby increasing system transparency, effectiveness, and trustworthiness. To provide personalized and interpret…
View article: Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries
Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries Open
In the era of foundation models and Large Language Models (LLMs), Euclidean space has been the de facto geometric setting for machine learning architectures. However, recent literature has demonstrated that this choice comes with fundament…
View article: Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning
Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning Open
Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend h…
View article: A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well? Open
As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonst…
View article: Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies
Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies Open
Political advertising plays a pivotal role in shaping public opinion and influencing electoral outcomes, often through subtle persuasive techniques embedded in broader propaganda strategies. Detecting these persuasive elements is crucial f…
View article: PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction Open
Autoregressive point cloud generation has long lagged behind diffusion-based approaches in quality. The performance gap stems from the fact that autoregressive models impose an artificial ordering on inherently unordered point sets, forcin…
View article: G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation
G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation Open
Explainable recommendation has demonstrated significant advantages in informing users about the logic behind recommendations, thereby increasing system transparency, effectiveness, and trustworthiness. To provide personalized and interpret…
View article: Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? Open
The radioactive nature of Large Language Model (LLM) watermarking enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models, making it a promising tool for preventing unauthor…
View article: A Survey of Personalized Large Language Models: Progress and Future Directions
A Survey of Personalized Large Language Models: Progress and Future Directions Open
Large Language Models (LLMs) excel in handling general knowledge tasks, yet they struggle with user-specific personalization, such as understanding individual emotions, writing styles, and preferences. Personalized Large Language Models (P…