Efficient Computing

Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation NAACL 2025 DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models ICLR 2025 Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs ICML 2025 DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization ACL 2025 DIDS: Domain Impact-aware Data Sampling for Large Language Model Training EMNLP 2025 DIESEL: A Lightweight Inference-Time Safety Enhancement for Language Models ACL 2025 DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting CVPR 2025 Differentiable and Learnable Wireless Simulation with Geometric Transformers ICLR 2025 Difficulty Diversity and Plausibility: Dynamic Data-Free Quantization WACV 2025 Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models ICLR 2025 Diffusion Sampling Correction via Approximately 10 Parameters ICML 2025 DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention CVPR 2025 DISC: Backpressure Mitigation In Multi-tier Applications With Distributed Shared Connection NSDI 2025 DiSCo: Device-Server Collaborative LLM-based Text Streaming Services ACL 2025 DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs ICCV 2025 Disentangling Text and Math in Word Problems: Evidence for the Bidimensional Structure of Large Language Models’ Reasoning ACL 2025 Disentangling the Dual Role of NIC Receive Rings OSDI 2025 Disentangling the Roles of Representation and Selection in Data Pruning ACL 2025 DispatchQA: A Benchmark for Small Function Calling Language Models in E-Commerce Applications EMNLP 2025 Dissecting and Streamlining the Interactive Loop of Mobile Cloud Gaming NSDI 2025 Distillation of Discrete Diffusion through Dimensional Correlations ICML 2025 Distillation Scaling Laws ICML 2025 Distilling Many-Shot In-Context Learning into a Cheat Sheet EMNLP 2025 Distributed Differentially Private Data Analytics via Secure Sketching ICML 2025 Distributed Event-Based Learning via ADMM ICML 2025