Searcharxiv⌕ Search

arXiv subjects

Jieyun Huang

Publications and source records attributed to Jieyun Huang.

8 recordsLinked to original sources

AdaMenu: Query-Adaptive Menus for Decision Models over Large Label Spaces

Decision models such as Jev return probabilities over caller-defined options and are increasingly used for classification. Large label spaces challenge both accuracy and scalability: larger menus can impair decisions, increase input costs, and exceed option limits. Hierarchical classification reduces menu size but introduces serial calls and error propagation. We propose AdaMenu, which builds a compact candidate menu from retrieved labeled examples and makes a single decision-model request. Its candidate labels adapt to the query, and its default setting also adjusts menu size using aggregated retrieval scores. We evaluate AdaMenu with open and closed decision models on four label sets containing up to 1,016 labels. It outperforms TypeSafe's beam-search baseline on all 16 model and label-set pairs where both methods run, improving accuracy by 16.6-34.3 percentage points. Relative to the full menu on the three smaller label sets, accuracy differences range from -0.5 to +7.2 percentage points, while input token usage falls by factors of 3.2-22.9. AdaMenu also runs when option limits exclude the full menu, including settings where the hierarchical baseline is unavailable.

cs.LG↗

HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents

Long-horizon agents compress interaction histories into memory, but final outcomes entangle memory-writing credit with tool failures and reasoning errors. We propose HiMPO, a Hindsight-Informed Memory Policy Optimization framework that supplements trajectory-level reinforcement learning with memory-specific credit. For each update, HiMPO compares the target answer's log-likelihood under the previous and updated memories while holding the remaining pre-write context fixed. A soft gate based on group-relative hindsight relevance then weights the local utility advantage. Trajectory-level credit applies to all generated tokens; memory tokens additionally receive the auxiliary advantage. Across judge-based open-domain tasks and objective compressive-memory QA, HiMPO improves task performance while preserving compressed-context efficiency. On Local Wiki Search, it improves average F1 and exact match over MemPO by 2.6 and 2.2 percentage points, respectively. Controlled interventions and live memory-reversion studies provide evidence of reduced blame leakage and alignment between memory credit and behavioral effects. With the policy fixed, the credit estimator remains robust to the tested forms of target noise.

cs.CL↗

ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification

Fraudulent messages sent via Short Message Service (SMS) are increasingly obfuscated to evade cost-conscious classifiers in production systems. In Chinese SMS, attackers can exploit a wide range of carefully crafted obfuscation strategies to hide risk-bearing phrases while preserving human readability, making direct classification brittle under real-world latency and throughput constraints. We propose ReCAST, a Restoration-aware Cascaded Stage-wise Training framework for robust obfuscated Chinese SMS classification. ReCAST distills a large teacher model's de-obfuscation ability into a smaller deployable student model by supervising obfuscated span detection, obfuscation type prediction, and text restoration, and then uses the restoration-aware student for downstream risk classification. Experiments on an internally constructed real-world Chinese SMS benchmark show that ReCAST substantially improves classification performance over directly trained baselines under obfuscation. The results suggest that restoration-aware distillation offers a practical path toward robust SMS risk classification with smaller deployable models under production-oriented constraints.

cs.CR↗

HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation

Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitations of rejection sampling. Standard methods treat the teacher as a static filter, discarding complex "corner-case" problems where the teacher fails to explore valid solutions independently, thereby creating an artificial "Teacher Ceiling" for the student. In this work, we propose Hindsight Entropy-Assisted Learning (HEAL), an RL-free framework designed to bridge this reasoning gap. Drawing on the educational theory of the Zone of Proximal Development (ZPD), HEAL synergizes three core modules: (1) Guided Entropy-Assisted Repair (GEAR), an active intervention mechanism that detects critical reasoning breakpoints via entropy dynamics and injects targeted hindsight hints to repair broken trajectories; (2) Perplexity-Uncertainty Ratio Estimator (PURE), a ratio-based filtering heuristic that reduces high-anomaly shortcut-like rationales; and (3) Progressive Answer-guided Curriculum Evolution (PACE), a three-stage distillation strategy that organizes training from foundational alignment to hard-case adaptation. Extensive experiments on multiple benchmarks demonstrate that HEAL significantly outperforms traditional SFT distillation and other baselines.

cs.AI↗

Token-Operations-Oriented Inference Optimization Techniques for Large Models

Large model inference optimization serves as a key foundation for supporting the scalable, low-cost, and highly stable operation of large model services. Centered on token-oriented inference optimization technology, this paper proposes for the first time a four-layer technical architecture consisting of Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion. It systematically reviews the key technologies and current industry status across these four levels and analyzes the application value of related technologies in real-world business scenarios. This paper provides a practical technical path for reducing token production costs, improving token service efficiency, ensuring the stability of token supply, and driving the transition of large model services from being merely callable to being operable.

cs.SE↗

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models

Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating redundant reasoning steps for simple problems), leading to excessive computational resource usage. While current mitigation strategies uniformly reduce reasoning tokens, they risk degrading performance on challenging tasks that require extended reasoning. This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty. We first propose a Token Length Budget (TLB) metric to quantify difficulty, then leverage budget-aware reward shaping and budget preference optimization to implement DAST. DAST penalizes overlong responses for simple tasks while incentivizing sufficient reasoning for complex problems. Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking (reducing token usage by over 30\% on average) while preserving reasoning accuracy on complex problems. Our codes and models are available at https://github.com/AnonymousUser0520/AnonymousRepo01.

cs.LG↗

Quantitative Analysis of Performance Drop in DeepSeek Model Quantization

Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers infrastructure simplicity, the models' 671B FP8 parameter configuration exceeds the practical memory limits of a standard 8-GPU machine. Quantization is a widely used technique that helps reduce model memory consumption. However, it is unclear what the performance of DeepSeek-R1 and V3 will be after being quantized. This technical report presents the first quantitative evaluation of multi-bitwidth quantization across the complete DeepSeek model spectrum. Key findings reveal that 4-bit quantization maintains little performance degradation versus FP8 while enabling single-machine deployment on standard NVIDIA GPU devices. We further propose DQ3_K_M, a dynamic 3-bit quantization method that significantly outperforms traditional Q3_K_M variant on various benchmarks, which is also comparable with 4-bit quantization (Q4_K_M) approach in most tasks. Moreover, DQ3_K_M supports single-machine deployment configurations for both NVIDIA H100/A100 and Huawei 910B. Our implementation of DQ3\_K\_M is released at https://github.com/UnicomAI/DeepSeek-Eval, containing optimized 3-bit quantized variants of both DeepSeek-R1 and DeepSeek-V3.

cs.LG↗

A Tensor-Based Sub-Mode Coordinate Algorithm for Stock Prediction

The investment on the stock market is prone to be affected by the Internet. For the purpose of improving the prediction accuracy, we propose a multi-task stock prediction model that not only considers the stock correlations but also supports multi-source data fusion. Our proposed model first utilizes tensor to integrate the multi-sourced data, including financial Web news, investors' sentiments extracted from the social network and some quantitative data on stocks. In this way, the intrinsic relationships among different information sources can be captured, and meanwhile, multi-sourced information can be complemented to solve the data sparsity problem. Secondly, we propose an improved sub-mode coordinate algorithm (SMC). SMC is based on the stock similarity, aiming to reduce the variance of their subspace in each dimension produced by the tensor decomposition. The algorithm is able to improve the quality of the input features, and thus improves the prediction accuracy. And the paper utilizes the Long Short-Term Memory (LSTM) neural network model to predict the stock fluctuation trends. Finally, the experiments on 78 A-share stocks in CSI 100 and thirteen popular HK stocks in the year 2015 and 2016 are conducted. The results demonstrate the improvement on the prediction accuracy and the effectiveness of the proposed model.

cs.LG↗