arXiv:2602.18758v1 Announce Type: cross Abstract: Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose UFO, a quantized 2PC inference framework that jointly optimizes the 2PC protocols and quantization algorithm. UFO features a novel 2PC protocol that systematically combines the efficient Winograd convolution algorithm with quantization to improve inference efficiency. However, we observe that naively combining quantization and Winograd convolution faces the following challenges: 1) From the inference perspective, Winograd transformations introduce extensive additions and require frequent bit width conversions to avoid inference overflow, leading to non-negligible communication overhead; 2) From the training perspective, Winograd transformations introduce weight outliers that make quantization-aware training (QAT) difficult, resulting in inferior model accuracy. To address these challenges, we co-optimize both protocol and algorithm. 1) At the protocol level, we propose a series of graph-level optimizations for 2PC inference to minimize the communication. 2) At the algorithm level, we develop a mixed-precision QAT algorithm based on layer sensitivity to optimize model accuracy given communication constraints. To accommodate the outliers, we further introduce a 2PC-friendly bit re-weighting algorithm to increase the representation range without explicitly increasing bit widths. With extensive experiments, UFO demonstrates 11.7x, 3.6x, and 6.3x communication reduction with 1.29%, 1.16%, and 1.29% higher accuracy compared to state-of-the-art frameworks SiRNN, COINN, and CoPriv, respectively.

arXiv:2512.22420v3 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load, compute-bound environments due to verification overhead. Existing Speculative Decoding strategies typically rely on static speculative lengths, failing to adapt to fluctuating request loads or identify the optimal moment to halt speculation. The cost of restarting speculative inference also remains unquantified. During traffic surges, the marginal utility of speculation diminishes; yet, the draft model's persistent memory footprint competes for available KV cache. This resource contention limits the maximum batch size, thereby degrading overall system throughput. To overcome this, we propose Nightjar, a resource-aware adaptive speculative framework. It first adjusts to the request load by dynamically selecting the optimal speculative length for different batch sizes. Crucially, upon detecting significant request queuing or KV cache shortages, it disables speculative decoding and offloads the draft model to the CPU. This reclaims memory for the KV cache, thereby facilitating larger batch sizes and maximizing overall system throughput. Experiments show that Nightjar achieves up to 27.29% higher throughput and 12.90% lower latency compared to standard speculative decoding under dynamic request arrival rates in real-time LLM serving scenarios.

arXiv:2602.15620v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. Our analysis shows that the magnitude of token-wise policy gradients in RL is negatively correlated with token probability and local policy entropy. We find that training instability can be caused by a tiny fraction of tokens, approximately 0.01%, which we term spurious tokens. When such tokens appear in correct responses, they contribute little to the reasoning outcome but inherit the full sequence-level reward, leading to abnormally amplified gradient updates. To mitigate this instability, we design an S2T (silencing spurious tokens) mechanism to efficiently identify spurious tokens through characteristic signals with low probability, low entropy, and positive advantage, and then suppress their gradient perturbations during optimization. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical reasoning benchmarks using Qwen 1.7B, 8B, and 14B base models, STAPO consistently demonstrates superior entropy stability and achieves an average performance improvement of 7.13% ($\rho_{\mathrm{T}}$=1.0, top-p=1.0) and 3.69% ($\rho_{\mathrm{T}}$=0.7, top-p=0.9) over GRPO, 20-Entropy, and JustRL.

arXiv:2512.00499v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving performance at scale often introduces a fundamental trade-off between training stability and training efficiency. Token-level optimization applies fine-grained updates at the individual units, but is prone to high variance in gradient estimation, which can result in unstable training dynamics. In contrast, Sequence-level optimization often relies on aggressive clipping mechanisms to ensure stable updates. However, such design may discard a large fraction of valid training samples, leading to inefficient gradient utilization and reduced training efficiency. We refer to this phenomenon as gradient underutilization. In this work, we propose Entropy Importance Sampling Policy Optimization (ESPO), a novel framework that aims to combine fine-grained updates with stable training. ESPO decomposes sequences into groups based on predictive entropy, enabling (1) Entropy Grouping Importance Sampling to capture intra-sequence heterogeneity, and (2) Entropy Adaptive Clipping to dynamically allocate trust regions based on model uncertainty. Extensive experiments on mathematical reasoning benchmarks demonstrate that ESPO not only accelerates convergence but also achieves state-of-the-art performance, notably improving accuracy on the challenging mathematical benchmarks.

arXiv:2512.22420v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, memory-bound systems but degrades performance in high-load, compute-bound environments due to verification overhead. Current SD implementations use a fixed speculative length, failing to adapt to dynamic request rates and creating a significant performance bottleneck in real-world serving scenarios. To overcome this, we propose Nightjar, a novel learning-based algorithm for adaptive speculative inference that adjusts to request load by dynamically selecting the optimal speculative length for different batch sizes and even disabling speculative decoding when it provides no benefit. Experiments show that Nightjar achieves up to 14.8% higher throughput and 20.2% lower latency compared to standard speculative decoding, demonstrating robust efficiency for real-time serving.