An Optimization Method for Autoregressive Time Series Forecasting

Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly by scaling up the model size rather than through genuinely autoregressive (AR) rollout. From the perspective of large language model training, the traditional training process for time-series forecasting models ignores temporal causality. In this paper, we propose a novel training method for time-series forecasting that enforces two key properties: (1) AR prediction errors should increase with the forecasting horizon. Any violation of this principle is considered random guessing and is explicitly penalized in the loss function, and (2) the method enables models to concatenate short-term AR predictions for forming flexible long-term forecasts. Empirical results demonstrate that our method establishes a new state-of-the-art across multiple benchmarks, achieving an MSE reduction of more than 10% compared to iTransformer and other recent strong baselines. Furthermore, it enables short-horizon forecasting models to perform reliable long-term predictions at horizons over 7.5 times longer. Code is available at https://github.com/LizhengMathAi/AROpt

Boosting Maximum Entropy Reinforcement Learning via One-Step Flow Matching

Diffusion policies are expressive yet incur high inference latency. Flow Matching (FM) enables one-step generation, but integrating it into Maximum Entropy Reinforcement Learning (MaxEnt RL) is challenging: the optimal policy is an intractable energy-based distribution, and the efficient log-likelihood estimation required to balance exploration and exploitation suffers from severe discretization bias. We propose \textbf{F}low-based \textbf{L}og-likelihood-\textbf{A}ware \textbf{M}aximum \textbf{E}ntropy RL (\textbf{FLAME}), a principled framework that addresses these challenges. First, we derive a Q-Reweighted FM objective that bypasses partition function estimation via importance reweighting. Second, we design a decoupled entropy estimator that rigorously corrects bias, which enables efficient exploration and brings the policy closer to the optimal MaxEnt policy. Third, we integrate the MeanFlow formulation to achieve expressive and efficient one-step control. Empirical results on MuJoCo show that FLAME outperforms Gaussian baselines and matches multi-step diffusion policies with significantly lower inference cost. Code is available at https://github.com/lzqw/FLAME.

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

RLVR is now a standard way to train LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency depends heavily on which prompts you sample and when. In practice, prompt pools are often static or only loosely tied to the model's learning progress, so uniform sampling can't keep up with the shifting capability frontier and ends up wasting rollouts on prompts that are already solved or still out of reach. Existing approaches improve efficiency through filtering, curricula, adaptive rollout allocation, or teacher guidance, but they typically assume a fixed pool-which makes it hard to support stable on-policy pool growth-or they add extra teacher cost and latency. We introduce HeaPA (Heap Sampling and On-Policy Query Augmentation), which maintains a bounded, evolving pool, tracks the frontier using heap-based boundary sampling, expands the pool via on-policy augmentation with lightweight asynchronous validation, and stabilizes correlated queries through topology-aware re-estimation of pool statistics and controlled reinsertion. Across two training corpora, two training recipes, and seven benchmarks, HeaPA consistently improves accuracy and reaches target performance with fewer computations while keeping wall-clock time comparable. Our analyses suggest these gains come from frontier-focused sampling and on-policy pool growth, with the benefits becoming larger as model scale increases. Our code is available at https://github.com/horizon-rl/HeaPA.

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and response sequences grow longer. Speculative decoding (SD) offers a powerful solution, providing significant speed-ups through its lightweight drafting and parallel verification mechanism. While existing work has nearly saturated improvements in draft effectiveness and efficiency, this paper advances SD from a new yet critical perspective: the verification cost. We propose TriSpec, a novel ternary SD framework that, at its core, introduces a lightweight proxy to significantly reduce computational cost by approving easily verifiable draft sequences and engaging the full target model only when encountering uncertain tokens. TriSpec can be integrated with state-of-the-art SD methods like EAGLE-3 to further reduce verification costs, achieving greater acceleration. Extensive experiments on the Qwen3 and DeepSeek-R1-Distill-Qwen/LLaMA families show that TriSpec achieves up to 35\% speedup over standard SD, with up to 50\% fewer target model invocations while maintaining comparable accuracy.

TeachBench: A Syllabus-Grounded Framework for Evaluating Teaching Ability in Large Language Models

Large language models (LLMs) show promise as teaching assistants, yet their teaching capability remains insufficiently evaluated. Existing benchmarks mainly focus on problem-solving or problem-level guidance, leaving knowledge-centered teaching underexplored. We propose a syllabus-grounded evaluation framework that measures LLM teaching capability via student performance improvement after multi-turn instruction. By restricting teacher agents to structured knowledge points and example problems, the framework avoids information leakage and enables reuse of existing benchmarks. We instantiate the framework on Gaokao data across multiple subjects. Experiments reveal substantial variation in teaching effectiveness across models and domains: some models perform well in mathematics, while teaching remains challenging in physics and chemistry. We also find that incorporating example problems does not necessarily improve teaching, as models often shift toward example-specific error correction. Overall, our results highlight teaching ability as a distinct and measurable dimension of LLM behavior.

Adaptive Reinforcement and Model Predictive Control Switching for Safe Human-Robot Cooperative Navigation

This paper addresses the challenge of human-guided navigation for mobile collaborative robots under simultaneous proximity regulation and safety constraints. We introduce Adaptive Reinforcement and Model Predictive Control Switching (ARMS), a hybrid learning-control framework that integrates a reinforcement learning follower trained with Proximal Policy Optimization (PPO) and an analytical one-step Model Predictive Control (MPC) formulated as a quadratic program safety filter. To enable robust perception under partial observability and non-stationary human motion, ARMS employs a decoupled sensing architecture with a Long Short-Term Memory (LSTM) temporal encoder for the human-robot relative state and a spatial encoder for 360-degree LiDAR scans. The core contribution is a learned adaptive neural switcher that performs context-aware soft action fusion between the two controllers, favoring conservative, constraint-aware QP-based control in low-risk regions while progressively shifting control authority to the learned follower in highly cluttered or constrained scenarios where maneuverability is critical, and reverting to the follower action when the QP becomes infeasible. Extensive evaluations against Pure Pursuit, Dynamic Window Approach (DWA), and an RL-only baseline demonstrate that ARMS achieves an 82.5 percent success rate in highly cluttered environments, outperforming DWA and RL-only approaches by 7.1 percent and 3.1 percent, respectively, while reducing average computational latency by 33 percent to 5.2 milliseconds compared to a multi-step MPC baseline. Additional simulation transfer in Gazebo and initial real-world deployment results further indicate the practicality and robustness of ARMS for safe and efficient human-robot collaboration. Source code and a demonstration video are available at https://github.com/21ning/ARMS.git.

VidLeaks: Membership Inference Attacks Against Text-to-Video Models

The proliferation of powerful Text-to-Video (T2V) models, trained on massive web-scale datasets, raises urgent concerns about copyright and privacy violations. Membership inference attacks (MIAs) provide a principled tool for auditing such risks, yet existing techniques - designed for static data like images or text - fail to capture the spatio-temporal complexities of video generation. In particular, they overlook the sparsity of memorization signals in keyframes and the instability introduced by stochastic temporal dynamics. In this paper, we conduct the first systematic study of MIAs against T2V models and introduce a novel framework VidLeaks, which probes sparse-temporal memorization through two complementary signals: 1) Spatial Reconstruction Fidelity (SRF), using a Top-K similarity to amplify spatial memorization signals from sparsely memorized keyframes, and 2) Temporal Generative Stability (TGS), which measures semantic consistency across multiple queries to capture temporal leakage. We evaluate VidLeaks under three progressively restrictive black-box settings - supervised, reference-based, and query-only. Experiments on three representative T2V models reveal severe vulnerabilities: VidLeaks achieves AUC of 82.92% on AnimateDiff and 97.01% on InstructVideo even in the strict query-only setting, posing a realistic and exploitable privacy risk. Our work provides the first concrete evidence that T2V models leak substantial membership information through both sparse and temporal memorization, establishing a foundation for auditing video generation systems and motivating the development of new defenses. Code is available at: https://zenodo.org/records/17972831.

HY-MT1.5 Technical Report

In this report, we introduce our latest translation models, HY-MT1.5-1.8B and HY-MT1.5-7B, a new family of machine translation models developed through a holistic training framework tailored for high-performance translation. Our methodology orchestrates a multi-stage pipeline that integrates general and MT-oriented pre-training, supervised fine-tuning, on-policy distillation, and reinforcement learning. HY-MT1.5-1.8B, the 1.8B-parameter model demonstrates remarkable parameter efficiency, comprehensively outperforming significantly larger open-source baselines (e.g., Tower-Plus-72B, Qwen3-32B) and mainstream commercial APIs (e.g., Microsoft Translator, Doubao Translator) in standard Chinese-foreign and English-foreign tasks. It achieves approximately 90% of the performance of ultra-large proprietary models such as Gemini-3.0-Pro, while marginally trailing Gemini-3.0-Pro on WMT25 and Mandarin-minority language benchmarks, it maintains a substantial lead over other competing models. Furthermore, HY-MT1.5-7B establishes a new state-of-the-art for its size class, achieving 95% of Gemini-3.0-Pro's performance on Flores-200 and surpassing it on the challenging WMT25 and Mandarin-minority language test sets. Beyond standard translation, the HY-MT1.5 series supports advanced constraints, including terminology intervention, context-aware translation, and format preservation. Extensive empirical evaluations confirm that both models offer highly competitive, robust solutions for general and specialized translation tasks within their respective parameter scales.

VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic approaches, we formally identify the cumulative reuse error effect and demonstrate how to minimize the non-prefix cache reuse error effectively. We further analyze the varying importance of model layers and propose a dynamic, layer-aware recomputation strategy to balance accuracy and efficiency. Experimental results show that VLCache achieves an accuracy on par with full recomputation, while requiring only 2-5% of the tokens to compute, yielding 1.2x-16x TTFT speedups. We develop an experimental implementation of the proposed VLCache pipeline based on SGLang, enabling significantly faster inference in practical deployments.

UltraDP: Generalizable Carotid Ultrasound Scanning with Force-Aware Diffusion Policy

Ultrasound scanning is a critical imaging technique for real-time, non-invasive diagnostics. However, variations in patient anatomy and complex human-in-the-loop interactions pose significant challenges for autonomous robotic scanning. Existing ultrasound scanning robots are commonly limited to relatively low generalization and inefficient data utilization. To overcome these limitations, we present UltraDP, a Diffusion-Policy-based method that receives multi-sensory inputs (ultrasound images, wrist camera images, contact wrench, and probe pose) and generates actions that are fit for multi-modal action distributions in autonomous ultrasound scanning of carotid artery. We propose a specialized guidance module to enable the policy to output actions that center the artery in ultrasound images. To ensure stable contact and safe interaction between the robot and the human subject, a hybrid force-impedance controller is utilized to drive the robot to track such trajectories. Also, we have built a large-scale training dataset for carotid scanning comprising 210 scans with 460k sample pairs from 21 volunteers of both genders. By exploring our guidance module and DP's strong generalization ability, UltraDP achieves a 95% success rate in transverse scanning on previously unseen subjects, demonstrating its effectiveness.