Optimization & Theory

Beyond scalar losses: calibrating segmentation models via gradient vector field surgery MIDL 2026 Beyond Single Solution: Multi-Hypothesis Deep Unfolding Network for Image Compressive Sensing CVPR 2026 Beyond Soft Label: Dataset Distillation via Orthogonal Gradient Matching CVPR 2026 Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation ACL 2026 Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data JMLR 2026 Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models CVPR 2026 BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers CVPR 2026 Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs ACL 2026 Block-based Learned Image Compression without Blocking Artifacts CVPR 2026 BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs ACL 2026 Brain Tumor Growth Inversion via Differentiable Neural Surrogates MIDL 2026 Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models ACL 2026 Bridging Domain Expertise and Generalization for Performance Estimation CVPR 2026 BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook ACL 2026 BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs ACL 2026 C^2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis CVPR 2026 Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference ACL 2026 Can LLM Safety Be Ensured by Constraining Parameter Regions? ACL 2026 Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation? ACL 2026 CaT-GS: Efficient 3DGS Rendering for Large-Scale Scenes with Inter-frame Caching and Tile Scheduling CVPR 2026 Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths ACL 2026 Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models CVPR 2026 Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring ACL 2026 Characterizing the Expressivity of Local Attention in Transformers ACL 2026 Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization CVPR 2026