3 accepted papers
We present APEX-Q, a flexible product quantization framework for compressing large language models. Unlike prior multi-codebook quantization methods with fixed partitions, APEX-Q supports arbitrary-dimensional tensor quantization, better capturing weight redundancy. It achieves performance on par wi
Current video understanding models struggle with temporal reasoning and efficient processing while balancing detail preservation with computational efficiency. We propose a hierarchical memory system that segments videos into action and scene units, combined with question-aware agentic keyframe sele
Extending LLM context windows is key for long-range tasks. RoPE-based position interpolation (PI) scales input length without retraining, and post-training quantization (PTQ) enables efficient deployment; however, combining PI with PTQ degrades accuracy due to long-context aliasing, dynamic-range di