5 papers
Composer 2 Technical Report
Cursor Research, :, Aaron Chan +53
Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability…
Attn-QAT: 4-Bit Attention With Quantization-Aware Training
Peiyuan Zhang, Matthew Noto, Wenxuan Tan +4
Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic…
Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths
Xuezhe Ma, Shicheng Wen, Linghao Jin +11
Designing a unified neural network to efficiently and inherently process sequential data with arbitrary lengths is a central and challenging problem in sequence modeling. The desig…
VSA: Faster Video Diffusion with Trainable Sparse Attention
Peiyuan Zhang, Yongqi Chen, Haofeng Huang +5
Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn…
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Zirui Zhang, Wei Hao, Aroon Sankoh +4
Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we…