21 accepted papers
Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, have successfully guided model development but fail to explain emerging non-monotonic phenomena such as catastrophic overtraining and quantization-induced degradation, where performance deteriorates despite i…
Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert overlap and overly uniform routing, which hinders expert speciali…
Enhancing the reasoning capabilities of language models (LMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making where existing Chain-of-Thought (CoT) approaches struggle with consistency and verification. In this paper, we propose a novel reasoning framew…
The cooperation of a pair of robot manipulators is required to manipulate a target object without any fixtures. The conventional control methods coordinate the end-effector pose of each manipulator with that of the other using their kinematics and joint coordinate measurements. Yet, the manipulators
Large Language Models (LLMs) have shown superior capability to solve reasoning problems with programs. While being a promising direction, most of such frameworks are trained and evaluated in settings with a prior knowledge of task requirements. However, as LLMs become more capable, it is necessary t…
Detecting and Grounding Multi-Modal Media Manipulation (DGM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> ) is an emerging task that aims to identify and locate manipulated elements in both textual and visual media. Given the complexity of thi…
Text-based Person Search (TBPS) aims to retrieve the person images based on the given text descriptions. Due to the heterogeneity between modalities and the fine granularity of the person, it is challenging to address the task. Existing methods often overlook granularity consistency across different…
Advancements in logical reasoning, utilizing LLMs to convert natural language into logical symbolism, combined with the use of external theorem provers, have repositioned the symbolic approach as a central point of interest. The main challenge within this paradigm lies in the LLMs’ capability to acc…
Conventional embedding-based models approach event time prediction in temporal knowledge graphs (TKGs) as a ranking problem. However, they often fall short in capturing essential temporal relationships such as order and distance. In this paper, we propose TEILP, a logical reasoning framework that na…
Inductive logic reasoning is a fundamental task in graph analysis, which aims to generalize patterns from data. This task has been extensively studied for traditional graph representations, such as knowledge graphs (KGs), using techniques like inductive logic programming (ILP). Existing ILP methods…
Despite current AI’s human-like behavior, super efficiency, and unbelievable ability to handle complex games, we still complain that it shows no sign of creativity, originality, or novelty outside its training set, and that it fails to develop new insights into old experience or establish understand…
Graph data, such as scene graphs and knowledge graphs, see wide use in AI systems. In real-world and large applications graph data are usually incomplete, motivating graph reasoning models for missing-fact or missing-relationship inference. While these models can achieve state-of-the-art performance…
Compared with static knowledge graphs, temporal knowledge graphs (tKG), which can capture the evolution and change of information over time, are more realistic and general. However, due to the complexity that the notion of time introduces to the learning of the rules, an accurate graph reasoning, e.…
Deep vision models have provided new capability across a spectrum of applications in transportation, manufacturing, agriculture, commerce, and security. However, recent studies have demonstrated that these models are vulnerable to adversarial attack, exposing a risk-of-use in critical applications w…
Due to the visual ambiguity, purely kinematic formulations on monocular human motion capture are often physically incorrect, biomechanically implausible, and can not reconstruct accurate interactions. In this work, we focus on exploiting the high-precision and non-differentiable physics simulator to…
A remote team of robots may be teleoperated by multiple users to explore unstructured environments and to tackle unforeseen emergencies therein. During a large-scale environmental search, each user may visually observe a unique hazard endangering the remote robot connected to their local robot. Ther…
In a distributed multi-master-multi-slave teleoperation system, the human users may compete against each other for the control of the team of slave robots. To win the competition, one operator would send the largest command to the slave group. For the sake of team cohesion, the slave group should fo…
Markov Logic Networks (MLNs), which elegantly combine logic rules and probabilistic graphical models, can be used to address many knowledge graph problems. However, inference in MLN is computationally intensive, making the industrial-scale application of MLN very difficult. In recent years, graph ne…
The capability of making interpretable and self-explanatory decisions is essential for developing responsible machine learning systems. In this work, we study the learning to explain the problem in the scope of inductive logic programming (ILP). We propose Neural Logic Inductive Learning (NLIL), an…
During swarm teleoperation, the operator may threaten the distance-dependent inter-robot communications and, with them, the connectivity of the slave swarm. To prevent the operator from disconnecting the swarm, this paper develops a constructive strategy to dynamically modulate the interconnections…
We study a general formulation of program synthesis called syntax-guided synthesis(SyGuS) that concerns synthesizing a program that follows a given grammar and satisfies a given logical specification. Both the logical specification and the grammar have complex structures and can vary from task to ta…