arXiv subjects

Duc Anh Le

Publications and source records attributed to Duc Anh Le.

5 recordsLinked to original sources

arXiv2026

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling

Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories. The key challenge is to maximize accuracy while minimizing the total number of generated tokens during reasoning. Recent PRM-guided methods score intermediate prefixes to steer this search, but most are frontier-only: they keep only the current active prefixes and irreversibly prune or resample away the rest using noisy PRM scores. This can cause premature commitment, diversity collapse, and the loss of prefixes that still admit correct continuations. We introduce stochastic backtracking over a persistent pool of historical prefixes, allowing test-time compute to revisit previously generated states instead of only expanding the current frontier. To make this efficient, we propose two complementary mechanisms. Subpool Selection strengthens greedy PRM-guided search by applying Top-N selection within random subpools, giving historical prefixes a chance to bypass over-scored frontier candidates. Power Backtrack Sequential Monte Carlo extends SMC-style resampling to the persistent pool using powered PRM scores and mixture-corrected weights. Across mathematical reasoning benchmarks and model scales, our methods consistently achieve higher accuracy per token count, and the same level of accuracy using only a fraction of the token count in comparison to strong PRM-guided baselines, demonstrating that persistent-pool stochastic backtracking provides a simple and effective way to improve the accuracy-token trade-off in test-time scaling.

cs.AI↗

arXiv2026

Selective Off-Policy Reference Tuning with Plan Guidance

Reinforcement learning with verifiable rewards helps reasoning, but GRPO-style methods stall on hard prompts where all sampled rollouts fail. SORT adds a repair update for those failures without changing rollout generation: it derives a plan from the reference solution, compares token probabilities with and without that plan, and gives higher weight to tokens that become more predictable under plan conditioning. This turns all-wrong prompts into selective, structure-aware learning signals instead of uniform imitation. Across three backbones and eight reasoning benchmarks, SORT improves over GRPO and guidance baselines, with largest gains on weaker models.

cs.AI↗

arXiv2024

Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking

Stack Overflow is a prominent Q and A forum, supporting developers in seeking suitable resources on programming-related matters. Having high-quality question titles is an effective means to attract developers' attention. Unfortunately, this is often underestimated, leaving room for improvement. Research has been conducted, predominantly leveraging pre-trained models to generate titles from code snippets and problem descriptions. Yet, getting high-quality titles is still a challenging task, attributed to both the quality of the input data (e.g., containing noise and ambiguity) and inherent constraints in sequence generation models. In this paper, we present FILLER as a solution to generating Stack Overflow post titles using a fine-tuned language model with self-improvement and post ranking. Our study focuses on enhancing pre-trained language models for generating titles for Stack Overflow posts, employing a training and subsequent fine-tuning paradigm for these models. To this end, we integrate the model's predictions into the training process, enabling it to learn from its errors, thereby lessening the effects of exposure bias. Moreover, we apply a post-ranking method to produce a variety of sample candidates, subsequently selecting the most suitable one. To evaluate FILLER, we perform experiments using benchmark datasets, and the empirical findings indicate that our model provides high-quality recommendations. Moreover, it significantly outperforms all the baselines, including Code2Que, SOTitle, CCBERT, M3NSCT5, and GPT3.5-turbo. A user study also shows that FILLER provides more relevant titles, with respect to SOTitle and GPT3.5-turbo.

cs.SE↗

arXiv2022

SAFL: A Self-Attention Scene Text Recognizer with Focal Loss

In the last decades, scene text recognition has gained worldwide attention from both the academic community and actual users due to its importance in a wide range of applications. Despite achievements in optical character recognition, scene text recognition remains challenging due to inherent problems such as distortions or irregular layout. Most of the existing approaches mainly leverage recurrence or convolution-based neural networks. However, while recurrent neural networks (RNNs) usually suffer from slow training speed due to sequential computation and encounter problems as vanishing gradient or bottleneck, CNN endures a trade-off between complexity and performance. In this paper, we introduce SAFL, a self-attention-based neural network model with the focal loss for scene text recognition, to overcome the limitation of the existing approaches. The use of focal loss instead of negative log-likelihood helps the model focus more on low-frequency samples training. Moreover, to deal with the distortions and irregular texts, we exploit Spatial TransformerNetwork (STN) to rectify text before passing to the recognition network. We perform experiments to compare the performance of the proposed model with seven benchmarks. The numerical results show that our model achieves the best performance.

cs.CV↗

arXiv2004

Charge Ordering Under a Magnetic Field in the Extended Hubbard Model

We study the charge ordering behavior under a magnetic field $H$ in the extended Hubbard model within the coherent potential approximation. At quarter filling, for small $H$ we find that the relative variation of critical temperature is quadratic with the coefficient $α$ smaller than the one for conventional spin-Peierls systems. For intermediate field, a melting of the charge ordering on decreasing temperature under fixed $H$ at various band filling is found.

cond-mat.str-el↗