跳转至

ACL 2026 · 全部收录(459 篇)

仅列出通过预过滤且已打分的论文;分数是「评测方法学价值」,不是会议录用质量。 返回总览

# 论文 轨道 分数 链接
451 Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics Long 2 页 · PDF
452 Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference Long 2 页 · PDF
453 d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models Long 2 页 · PDF
454 MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning Long 2 页 · PDF
455 PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning Long 2 页 · PDF
456 QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis Long 2 页 · PDF
457 XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts Long 2 页 · PDF
458 DecoCal: Decoding with Calibration in Diffusion Large Language Models Long 1 页 · PDF
459 From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration Long 1 页 · PDF

评论