相关论文: Winning the CVPR'2022 AQTC Challenge: A Two-stage …

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…

Multi-relation question answering (QA) is a challenging task, where given questions usually require long reasoning chains in KGs that consist of multiple relations. Recently, methods with explicit multi-step reasoning over KGs have been…

This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer…

In this paper we propose the CTS (Concious Tutoring System) technology, a biologically plausible cognitive agent based on human brain functions.This agent is capable of learning and remembering events and any related information such as…

Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have…

Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to…

In this paper, we present the runner-up solution for the Ego4D EgoSchema Challenge at CVPR 2025 (Confirmed on May 20, 2025). Inspired by the success of large models, we evaluate and leverage leading accessible multimodal large models and…

Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…

Despite recent progress in video large language models (VideoLLMs), a key open challenge remains: how to equip models with chain-of-thought (CoT) reasoning abilities grounded in fine-grained object-level video understanding. Existing…

Egocentric action anticipation consists in predicting a future action the camera wearer will perform from egocentric video. While the task has recently attracted the attention of the research community, current approaches assume that the…

High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These…

This paper presents a cognitive tutor powered by Davinci 003 API that generates and evaluates personalized questions for students on any topic they choose. The tutor adapts to the student's level of understanding and fosters knowledge…

This technical brief introduces Deep Agent, an advanced autonomous AI system designed to manage complex multi-phase tasks through a novel hierarchical task management architecture. The system's foundation is built on our Hierarchical Task…

Automatic question generation (AQG) for mathematics education remains an elusive goal for Intelligent Tutoring Systems and educators. While pre-trained transformer-based language models have significantly advanced natural language…

We present a two-phase vision-language QA system for autonomous driving that answers high-level perception, prediction, and planning questions. In Phase-1, a large multimodal LLM (Qwen2.5-VL-32B) is conditioned on six-camera inputs, a short…

Knowledge tracing (KT) is a popular approach for modeling students' learning progress over time, which can enable more personalized and adaptive learning. However, existing KT approaches face two major limitations: (1) they rely heavily on…

The goal of query performance prediction (QPP) is to automatically estimate the effectiveness of a search result for any given query, without relevance judgements. Post-retrieval features have been shown to be more effective for this task…

Almost all Computer Science programs require students to take a course on the Theory of Computation (ToC) which covers various models of computation such as finite automata, push-down automata and Turing machines. ToC courses tend to give…

A successful Machine Learning (ML) model implementation requires three main components: training dataset, suitable model architecture and training procedure. Given dataset and task, finding an appropriate model might be challenging. AutoML,…

The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perform well. However, their performance improves further by…