Related papers: Automated Bug Frame Retrieval from Gameplay Videos…
The complexity of code reviews has driven efforts to automate review comments, but prior approaches oversimplify this task by treating it as snippet-level code-to-text generation and relying on text similarity metrics like BLEU for…
Compile-pass rate is the dominant evaluation signal for LLM code generation, yet for multi-component domain-specific artifacts it can be actively misleading. We demonstrate this on executable game scene synthesis with a four-axis evaluation…
Multimodal large language models are increasingly used as agent backbones that understand multimodal inputs, plan retrieval actions, invoke external tools, and reason over retrieved information. Yet existing benchmarks rarely evaluate this…
Video understanding, including video captioning and retrieval, is still a great challenge for video-language models (VLMs). The existing video retrieval and caption benchmarks only include short descriptions, limits their ability of…
The rapid pace of large-scale software development places increasing demands on traditional testing methodologies, often leading to bottlenecks in efficiency, accuracy, and coverage. We propose a novel perspective on software testing by…
Generating coherent and useful image/video scenes from a free-form textual description is technically a very difficult problem to handle. Textual description of the same scene can vary greatly from person to person, or sometimes even for…
Achieving a desirable balance between rendering quality and real-time performance is a long-standing challenge in modern game and rendering engines, particularly on resource-constrained mobile devices such as laptops, tablets, and…
Real-time rendering for video games has become increasingly challenging due to the need for higher resolutions, framerates and photorealism. Supersampling has emerged as an effective solution to address this challenge. Our work introduces a…
Video game development increasingly relies on using visual programming languages as the primary way to build video game features. The aim of using visual programming is to move game logic into the hands of game designers, who may not be as…
Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generative camera systems can produce diverse, text-conditioned…
Detecting actions in videos, particularly within cluttered scenes, poses significant challenges due to the limitations of 2D frame analysis from a camera perspective. Unlike human vision, which benefits from 3D understanding, recognizing…
Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video…
Multimodal large language models (MLLMs) represent images and video frames as visual tokens. Scaling from single images to hour-long videos, however, inflates the token budget far beyond practical limits. Popular pipelines therefore either…
One of the primary mechanisms by which developers receive feedback about in-field failures of software from users is through bug reports. Unfortunately, the quality of manually written bug reports can vary widely due to the effort required…
Action recognition, an essential component of computer vision, plays a pivotal role in multiple applications. Despite significant improvements brought by Convolutional Neural Networks (CNNs), these models suffer performance declines when…
Prompt engineering plays a critical role in adapting large language models (LLMs) to complex reasoning and labeling tasks without the need for extensive fine-tuning. In this paper, we propose a novel prompt optimization pipeline for frame…
Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common…
Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatial or semantic context. Recent video anomaly localization and…
Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…
We introduce an approach to generating videos based on a series of given language descriptions. Frames of the video are generated sequentially and optimized by guidance from the CLIP image-text encoder; iterating through language…