3 papers
cs.CL2026
Offline Guidance, Online Reasoning: Reusing LLM Feedback for Small Language Models
Bohan Zhang, Linan Yue, Weibo Gao +3
Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (SLMs) are easier to deploy loc…
cs.DC2026
APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing
Hong Guo, Nianhui Guo, Weixing Wang +3
W4A4 quantization promises full utilization of INT4 Tensor Cores, yet group dequantization overhead on CUDA Cores has driven existing systems to mixed-precision fallbacks. We prese…
cs.LG2026
Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling
Hong Guo, Nianhui Guo, Christoph Meinel +1
Sampling from the sequence-level power distribution elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings…