Jue WANG

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time

Think Deep, Think Fast: Investigating Efficiency of Trained-verifier-free Inference-time-scaling Methods

Mixture-of-Agents Enhances Large Language Model Capabilities

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

Improving Model Alignment Through Collective Intelligence of Open-Source Models

Scaling Instruction-tuned LLMs to Million-token Contexts via Hierarchical Synthetic Data Generation

FloE: On-the-Fly MoE Inference on Memory-constrained GPU

Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping

Ladder Residual: Redefining Tensor Parallelism in Transformers for Accelerated Inference

Improving Model Alignment Through Collective Intelligence of Open-Source Models