The Thirty-Ninth Annual Conference on Neural Information Processing Systems

Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment

2025

The Thirty-Ninth Annual Conference on Neural Information Processing Systems

Learning to Better Search with Language Models via Guided Reinforced Self-Training

2025

The Thirty-Ninth Annual Conference on Neural Information Processing Systems

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

2025

Forty-Second International Conference on Machine Learning

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance

2025

The Forty-First International Conference on Machine Learning

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging

2024