Paper-Conference

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints

Tool Playgrounds: A Comprehensive and Analyzable Benchmark for LLM Tool Invocation

Robust long-tailed recognition with distribution-aware adversarial example generation

ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding

Past-Future Scheduler for LLM Serving under SLA Guarantees

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models