33 accepted papers
Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on simplistic filtering mechanisms to select prompt datasets within…
With the rapid advancement of generative models, generated image detection has become an important task in visual forensics. Although existing methods have achieved remarkable progress, they often rely, after training, on only a small subset of highly salient forgery cues, which limits their ability
Generative models continue to advance rapidly in both fidelity and diversity, posing increasing challenges for reliably distinguishing generated images from real ones. Existing reconstruction-based detection methods often rely on assumptions tied to specific generative models, which leads to limited
Offline reinforcement learning enables policy learning solely from fixed datasets, without costly or risky environment interactions, making it highly valuable for real-world applications. While Transformer-based approaches have recently demonstrated strong sequence modeling capabilities, they typica…
Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific constraints like safety. Typically, constrained optimization prob
LLM-driven agents demonstrate strong performance in sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. This insufficient experience reuse leads to computational redundancy and execution instability. To bridge this gap, we propose Pro…
Humans can imagine and manipulate visual images mentally, a capability known as \textit{spatial visualization}. While many multi-modal benchmarks assess reasoning on visible visual information, the ability to infer unseen relationships through spatial visualization remains insufficiently evaluated…
Bio-inspired aquatic propulsion offers high thrust and maneuverability but is prone to destabilizing forces such as lift fluctuations, which are further amplified by six-degree-of-freedom (6-DoF) fluid coupling. We formulate quadrupedal swimming as a constrained optimization problem that maximizes f…
Economic decision‑making depends not only on structured signals—such as prices and taxes—but also on unstructured language, including peer dialogue and media narratives. While multi‑agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic
When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. However, in truly open-ended environments, the apparent causal mechanism may drift over time because the agent continually encount…
Artificial intelligence (AI) has become a powerful tool for economic research, enabling large-scale simulation and policy optimization. However, applying AI effectively requires simulation platforms for scalable training and evaluation—yet existing environments remain limited to simplified, narrowly…
In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing across diverse environments due to their limited grasp of the u…
Simulating collective decision-making involves more than aggregating individual behaviors; it emerges from dynamic interactions among individuals. While large language models (LLMs) offer strong potential for social simulation, achieving quantitative alignment with real-world data remains a key chal…
Advanced large language models (LLMs) frequently reflect in reasoning chain-of-thoughts (CoTs), where they self-verify the correctness of current solutions and explore alternatives. However, given recent findings that LLMs detect limited errors in CoTs, how reflection contributes to empirical improv…
The rapid advancement of generative models has significantly improved the quality of generated images. Meanwhile, it challenges information authenticity and credibility. Current generated image detection methods based on large-scale pre-trained multimodal models have achieved impressive results. Alt…
The application of artificial intelligence technology has greatly enhanced and fortified the safety of energy pipelines, particularly in safeguarding against external threats. The predominant methods involve the integration of intelligent sensors to detect external vibration, enabling the identifica…
Between 2021 and 2023, AI-Olympics---a series of online AI competitions, was hosted by the online evaluation platform Jidi in collaboration with the IJCAI committee. In these competitions, an agent is required to accomplish diverse sports tasks in a two-dimensional continuous world, while competing…
Presents corrections to the article “UWB-VIO Fusion for Accurate and Robust Relative Localization of Round Robotic Teams”.
With the continued advancement of Large Language Models (LLMs) Agents in reasoning, planning, and decision-making, benchmarks have become crucial in evaluating these skills. However, there is a notable gap in benchmarks for real-time strategic decision-making. StarCraft II (SC2), with its complex an…
Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication…
Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the evaluation of full answers generated by the models. However, the…
The goal of zero-shot human-AI coordination is to develop an agent that can collaborate with humans without relying on human data. Prevailing two-stage population-based methods require a diverse population of mutually distinct policies to simulate diverse human behaviors. The necessity of such popul…
Fast and flexible dense reconstruction has been extensively studied due to its wide application. Considering the efficiency of multi-robot systems, cooperative reconstruction is gaining attention. Classic methods rely on inter-robot loop closures, which cannot work when there is no common area betwe
Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations. In this paper, we develop a unified framework that describes variations of GMRL…
The Elo rating system is widely adopted to evaluate the skills of (chess) game and sports players. Recently it has been also integrated into machine learning algorithms in evaluating the performance of computerised AI agents. However, an accurate estimation of the Elo rating (for the top players) of…
As an emerging technology of computer-aided education, cognitive modeling aims at discovering the knowledge proficiency or learning ability of students, which can enable a wide range of intelligent educational applications. While considerable efforts have been made in this direction, a long-standing…
The relative pose estimation is one of the most fundamental components for multi-robot systems, while it still remains an open and challenging research topic in infrastructure-free environment. In this letter, we target improving the accuracy and robustness of relative pose estimation for ground rob
Multi-agent evaluation aims at the assessment of an agent’s strategy on the basis of interaction with others. Typically, existing methods such as $\alpha$-rank and its approximation still require to exhaustively compare all pairs of joint strategies for an accurate ranking, which in practice is comp…
Oil and gas pipelines are known as the backbone of global energy, and securing their safety is crucial for energy supply. In this study, we utilized a novel machine learning method based on the spatiotemporal features of distributed optical fiber sensor signals to monitor the safety of oil and gas p…
Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL (MARL), although the PG theorem can be naturally extended, the effectiveness of multi-agent PG (MAPG) methods degrades as th…
Knowledge tracing (KT) defines the task of predicting whether students can correctly answer questions based on their historical response. Although much research has been devoted to exploiting the question information, plentiful advanced information among questions and skills hasn't been well extract…
To extract crucial local features and enhance the complementary relation between local and global features, this paper proposes a Weakly Supervised Local-Global Relation Network (WS-LGRN), which uses the attention mechanism to deal with part location and feature fusion problems. Firstly, the Attenti…
Research shows that the facial expression recognition is strongly related to the person's identity. This paper presents an expression-identity fusion network to address the great inter-subject variations in facial expression recognition. The model is designed to jointly learn identity-related featur…