Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capability of Large Language Models (LLMs). Current RLVR approaches typically conduct training across all generated tokens, but neglect to explore which tokens (e.g., prefix tokens) actually contribute to reasoning. This uniform training strategy spends substantial effort on optimizing low-return tokens, which in turn impedes the potential improvement from high-return tokens and reduces overall training effectiveness. To address this issue, we propose a novel RLVR approach called Progressive Prefix-token Policy Optimization (PPPO), which highlights the significance of the prefix segment of generated outputs. Specifically, inspired by the well-established human thinking theory of Path Dependence, where early-stage thoughts substantially constrain subsequent thinking trajectory, we identify an analogous phenomenon in LLM reasoning termed Beginning Lock-in Effect (BLE). PPPO leverages this finding by focusing its optimization objective on the prefix reasoning process of LLMs. This targeted optimization strategy can positively influence subsequent reasoning processes, and ultimately improve final results. To improve the learning effectiveness of LLMs on how to start reasoning with high quality, PPPO introduces two training strategies: (a) Progressive Prefix Retention, which shapes a progressive learning process by increasing the proportion of retained prefix tokens during training; (b) Continuation Accumulated Reward, which mitigates reward bias by sampling multiple continuations for one prefix token sequence, and accumulating their scores as the reward signal. Extensive experimental results on various reasoning tasks demonstrate that our proposed PPPO outperforms representative RLVR methods, with the accuracy improvements of 18.02% on only 26.17% training tokens.

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning

Recently, offline reinforcement learning (RL) has become a popular RL paradigm. In offline RL, data providers share pre-collected datasets -- either as individual transitions or sequences of transitions forming trajectories -- to enable the training of RL models (also called agents) without direct interaction with the environments. Offline RL saves interactions with environments compared to traditional RL, and has been effective in critical areas, such as navigation tasks. Meanwhile, concerns about privacy leakage from offline RL datasets have emerged. To safeguard private information in offline RL datasets, we propose the first differential privacy (DP) offline dataset synthesis method, PrivORL, which leverages a diffusion model and diffusion transformer to synthesize transitions and trajectories, respectively, under DP. The synthetic dataset can then be securely released for downstream analysis and research. PrivORL adopts the popular approach of pre-training a synthesizer on public datasets, and then fine-tuning on sensitive datasets using DP Stochastic Gradient Descent (DP-SGD). Additionally, PrivORL introduces curiosity-driven pre-training, which uses feedback from the curiosity module to diversify the synthetic dataset and thus can generate diverse synthetic transitions and trajectories that closely resemble the sensitive dataset. Extensive experiments on five sensitive offline RL datasets show that our method achieves better utility and fidelity in both DP transition and trajectory synthesis compared to baselines. The replication package is available at the GitHub repository.

Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis

In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this conclusion is incomplete and overlooks the challenge of densely correlated datasets, where intricate dependencies can overwhelm statistical models. In such complex scenarios, neural networks are more suitable due to their capacity to fit complex distributions by learning directly from samples. Despite this potential, existing NN-based algorithms still suffer from significant limitations. We therefore propose MargNet, incorporating successful algorithmic designs of statistical models into neural networks. MargNet applies an adaptive marginal selection strategy and trains the neural networks to generate data that conforms to the selected marginals. On sparsely correlated datasets, our approach achieves utility close to the best statistical method while offering an average 7$\times$ speedup over it. More importantly, on densely correlated datasets, MargNet establishes a new state-of-the-art, reducing fidelity error by up to 26\% compared to the previous best. We release our code on GitHub.\footnote{https://github.com/KaiChen9909/margnet}

The Analysis and Performance of LODC-OFDM Signal in Nonlinear Rydberg Atomic Sensor

Rydberg atomic sensors have been seen as novel radio frequency (RF) measurements and the high sensitivity to a large range of frequencies makes it attractive for communications reception. However, the signal sensing process in Rydberg system involves sequential transduction from electromagnetic waves to optical signals and finally to electrical signals. The unipolar characteristic of the optical interface inherently restricts conventional OFDM reception. Therefore, adopting unipolar OFDM schemes, inspired by optical communication systems, becomes essential for compatible signal transmission. In this work, we investigate the amplitude modulation-to-amplitude modulation (AM-AM) characteristics of Rydberg atomic sensors, establishing an empirical approximation function. Building on the direct current-biased optical orthogonal frequency division multiplexing (DCO-OFDM) framework, we propose a novel local oscillator direct current-biased OFDM (LODC-OFDM) scheme specifically optimized for Rydberg-based sensing, effectively addressing the broadband OFDM reception challenge. Then, we adopt Bussgang theorem to analyze the nonlinear distortion of LODC-OFDM signals and the results in closed-form solutions are derived for AM/AM curves approximated by Taylor series expansion and for the ideal pre-distortion case. In real experiments, the experimental and theoretical results fit well.

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine whether to reason for a given problem, they typically lack a fine-grained mechanism to modulate how much to reason. This often results in a ``one-size-fits-all'' reasoning depth, which generates redundant overthinking for simple questions while failing to allocate sufficient thought to complex ones. In this paper, we conduct an in-depth analysis of LALMs and find that an effective and efficient LALM should reason smartly by adapting its reasoning depth to the problem's complexity. To achieve this, we propose a difficulty-adaptive reasoning method for LALMs. Specifically, we propose a reward function that dynamically links reasoning length to the model's perceived problem difficulty. This reward encourages shorter, concise reasoning for easy tasks and more elaborate, in-depth reasoning for complex ones. Extensive experiments demonstrate that our method is both effective and efficient, simultaneously improving task performance and significantly reducing the average reasoning length. Further analysis on reasoning structure paradigm offers valuable insights for future work.

Text-driven Multiplanar Visual Interaction for Semi-supervised Medical Image Segmentation

Semi-supervised medical image segmentation is a crucial technique for alleviating the high cost of data annotation. When labeled data is limited, textual information can provide additional context to enhance visual semantic understanding. However, research exploring the use of textual data to enhance visual semantic embeddings in 3D medical imaging tasks remains scarce. In this paper, we propose a novel text-driven multiplanar visual interaction framework for semi-supervised medical image segmentation (termed Text-SemiSeg), which consists of three main modules: Text-enhanced Multiplanar Representation (TMR), Category-aware Semantic Alignment (CSA), and Dynamic Cognitive Augmentation (DCA). Specifically, TMR facilitates text-visual interaction through planar mapping, thereby enhancing the category awareness of visual features. CSA performs cross-modal semantic alignment between the text features with introduced learnable variables and the intermediate layer of visual features. DCA reduces the distribution discrepancy between labeled and unlabeled data through their interaction, thus improving the model's robustness. Finally, experiments on three public datasets demonstrate that our model effectively enhances visual features with textual information and outperforms other methods. Our code is available at https://github.com/taozh2017/Text-SemiSeg.

Label-free Super-Resolution Microvessel Color Flow Imaging with Ultrasound

We present phase subtraction imaging (PSI), a new spatial-temporal beamforming method that enables micrometer level resolution imaging of microvessels in live animals without labels, which are microbubbles in ultrasound super-resolution imaging. Subtraction of relative phase differences between consecutive frames beamformed with mismatched apodizations is used in PSI to overcome the diffraction limit. We validated this method by imaging both the mouse brain and rabbit kidney using different ultrasound probes and scanning machines.

A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices

The demand for machine learning (ML) model training on edge devices is escalating due to data privacy and personalized service needs. However, we observe that current on-device model training is hampered by the under-utilization of on-device data, due to low training throughput, limited storage and diverse data importance. To improve data resource utilization, we propose a two-stage data selection framework {\sf Titan} to select the most important data batch from streaming data for model training with guaranteed efficiency and effectiveness. Specifically, in the first stage, {\sf Titan} filters out a candidate dataset with potentially high importance in a coarse-grained manner.In the second stage of fine-grained selection, we propose a theoretically optimal data selection strategy to identify the data batch with the highest model performance improvement to current training round. To further enhance time-and-resource efficiency, {\sf Titan} leverages a pipeline to co-execute data selection and model training, and avoids resource conflicts by exploiting idle computing resources. We evaluate {\sf Titan} on real-world edge devices and three representative edge computing tasks with diverse models and data modalities. Empirical results demonstrate that {\sf Titan} achieves up to $43\%$ reduction in training time and $6.2\%$ increase in final accuracy with minor system overhead, such as data processing delay, memory footprint and energy consumption.

From Rankings to Insights: Evaluation Should Shift Focus from Leaderboard to Feedback

Automatic evaluation benchmarks such as MT-Bench, Arena-Hard, and Auto-Arena are seeing growing adoption for the evaluation of Large Language Models (LLMs). Existing research has primarily focused on approximating human-based model rankings using limited data and LLM-as-a-Judge. However, the fundamental premise of these studies, which attempts to replicate human rankings, is flawed. Specifically, these benchmarks typically offer only overall scores, limiting their utility to leaderboard rankings, rather than providing feedback that can guide model optimization and support model profiling. Therefore, we advocate for an evaluation paradigm shift from approximating human-based model rankings to providing feedback with analytical value. To this end, we introduce Feedbacker, an evaluation framework that provides comprehensive and fine-grained results, thereby enabling thorough identification of a model's specific strengths and weaknesses. Such feedback not only supports the targeted optimization of the model but also enhances the understanding of its behavior. Feedbacker comprises three key components: an extensible tree-based query taxonomy builder, an automated query synthesis scheme, and a suite of visualization and analysis tools. Furthermore, we propose a novel LLM-as-a-Judge method: PC2 (Pre-Comparison-derived Criteria) pointwise evaluation. This method derives evaluation criteria by pre-comparing the differences between several auxiliary responses, achieving the accuracy of pairwise evaluation while maintaining the time complexity of pointwise evaluation. Finally, leveraging the evaluation results of 17 mainstream LLMs, we demonstrate the usage of Feedbacker and highlight its effectiveness and potential. Our homepage project is available at https://liudan193.github.io/Feedbacker.

Self-Correction Makes LLMs Better Parsers

Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep language understanding, particularly syntactic parsing. In this paper, we conduct an in-depth analysis of LLM parsing capabilities, delving into the specific shortcomings of their parsing results. We find that LLMs may stem from limitations to fully leverage grammar rules in existing treebanks, which restricts their capability to generate valid syntactic structures. To help LLMs acquire knowledge without additional training, we propose a self-correction method that leverages grammar rules from existing treebanks to guide LLMs in correcting previous errors. Specifically, we automatically detect potential errors and dynamically search for relevant rules, offering hints and examples to guide LLMs in making corrections themselves. Experimental results on three datasets with various LLMs, demonstrate that our method significantly improves performance in both in-domain and cross-domain settings on the English and Chinese datasets.