Related papers: SimStep: Chain-of-Abstractions for Incremental Spe…
The rapid evolution of large language models in natural language processing has substantially elevated their semantic understanding and logical reasoning capabilities. Such proficiencies have been leveraged in autonomous driving systems,…
This paper proposes a novel 3D speech-to-animation (STA) generation framework designed to address the shortcomings of existing models in producing diverse and emotionally resonant animations. Current STA models often generate animations…
The escalating complexity of software systems and accelerating development cycles pose a significant challenge in managing code errors and implementing business logic. Traditional techniques, while cornerstone for software quality…
Semantic segmentation is a core task in computer vision. Existing methods are generally divided into two categories: automatic and interactive. Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as…
Collaborations with Generative AI often begin with a short prompt and end with an opaque output, leaving implicit who was involved, what task was being pursued, which resources were used, and which constraints should have shaped the…
Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes. Therefore,…
For the past decade, the trajectory of generative artificial intelligence (AI) has been dominated by a model-centric paradigm driven by scaling laws. Despite significant leaps in visual fidelity, this approach has encountered a ``usability…
Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…
Chain-of-Thought (CoT) reasoning, which breaks down complex tasks into intermediate reasoning steps, has significantly enhanced the performance of large language models (LLMs) on challenging tasks. However, the detailed reasoning process in…
Abstract reasoning, the ability to reason from the abstract essence of a problem, serves as a key to generalization in human reasoning. However, eliciting language models to perform reasoning with abstraction remains unexplored. This paper…
Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. Due to incomplete or excessive class activation, existing studies often resort to offline CAM refinement,…
Large Language Models (LLMs) demonstrate the ability to solve reasoning and mathematical problems using the Chain-of-Thought (CoT) technique. Expanding CoT length, as seen in models such as DeepSeek-R1, significantly enhances this reasoning…
External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…
The introductory programming sequence has been the focus of much research in computing education. The recent advent of several viable and freely-available AI-driven code generation tools present several immediate opportunities and…
Instructions augmentation is a crucial step for unleashing the full potential of large language models (LLMs) in downstream tasks. Existing Self-Instruct methods primarily simulate new instructions from a few initial instructions with…
Full-text error correction with Large Language Models (LLMs) for Automatic Speech Recognition (ASR) is attracting increased attention for its ability to address a wide range of error types, such as punctuation restoration and inverse text…
Drama-in-education is an interdisciplinary instructional approach that integrates subjects such as language, history, and psychology. Its core component is playwriting. Based on need-finding interviews of 13 teachers, we found that current…
Language model-based code generation and completion tools have been widely adopted, but they may sometimes produce code that does not meet necessary constraints, such as syntactic correctness or API existence. Constrained decoding…
Generative AI is reshaping higher education programming through vibe coding, where students collaborate with AI via natural language rather than writing code line-by-line. We conceptualize this practice as help-seeking, analyzing 19,418…
Generative AI has democratized content creation, but popular chatbot-based interfaces often prioritize execution, generating fully rendered artifacts right away. This issue can lead to premature convergence and design fixation, where users…