Deep Learning

Scaling Effects on Latent Representation Edits in GPT Models (Student Abstract) AAAI 2025 Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement NAACL 2025 Scaling Inference Time Compute for Diffusion Models CVPR 2025 Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension ICCV 2025 Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport ICLR 2025 Scaling Language-Free Visual Representation Learning ICCV 2025 Scaling Large Motion Models with Million-Level Human Motions ICML 2025 Scaling Laws and Efficient Inference for Ternary Language Models ACL 2025 Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check EMNLP 2025 Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens ICLR 2025 Scaling Laws for Floating–Point Quantization Training ICML 2025 Scaling Laws for Multilingual Language Models ACL 2025 Scaling Laws for Native Multimodal Models ICCV 2025 Scaling Laws for Synthetic Speech for Model Training Interspeech 2025 Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream ICML 2025 Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More ICML 2025 Scaling LLMs’ Social Reasoning: Sprinkle Cognitive “Aha Moment” into Fundamental Long-thought Logical Capabilities ACL 2025 Scaling Low-Resource MT via Synthetic Data Generation with LLMs EMNLP 2025 Scaling Mesh Generation via Compressive Tokenization CVPR 2025 Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities ICCV 2025 Scaling Optimal LR Across Token Horizons ICLR 2025 Scaling Probabilistic Circuits via Monarch Matrices ICML 2025 Scaling Properties of Diffusion Models For Perceptual Tasks CVPR 2025 Scaling pseudo-labeling data for end-to-end low-resource speech translation (the case of Kurdish language) Interspeech 2025 Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study ICLR 2025