4 papers · 1 filter
Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL
Chuyi Tan, Peiwen Yuan, Xinglin Wang +8
Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models (LLMs) but is bottlenecked by scarce labeled data. Reinforce…
PatternKV: Flattening KV Representation Expands Quantization Headroom
Ji Zhang, Yiwei Li, Shaoxiong Feng +8
KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and…
Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
Xinglin Wang, Yiwei Li, Shaoxiong Feng +7
Test-Time Scaling (TTS) improves the performance of Large Language Models (LLMs) by using additional inference-time computation to explore multiple reasoning paths through search.…
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng +7
Evaluating models on large benchmarks is very resource-intensive, especially during the period of rapid model evolution. Existing efficient evaluation methods estimate the performa…