QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks

Low-bit quantization is widely used to compress super-resolution (SR) models and reduce storage and computation costs for deployment on resource-limited devices. However, when SR models are pushed to ultra-low precision (2-4 bits), performance can drop sharply due to diminished representational capacity and the detail-sensitive nature of SR. To address these issues, we propose QuantSR+, a unified framework that improves quantization operators, network design, and training optimization, achieving better trade-offs between accuracy and efficiency than prior low-bit SR methods. QuantSR+ mainly relies on three technical contributions: (1) Redistribution-driven Bit Determination (RBD), which reshapes quantization distributions in both forward and backward passes to preserve representation fidelity; (2) Quantized Slimmable Architecture (QSA), which begins with an over-parameterized model and progressively prunes less critical blocks to meet efficiency budgets while pushing the accuracy performance; and (3) Slimming-guided Function-localized Distillation (SFD), which enforces block-aware feature alignment via a direct loss and a progressive, function-local training schedule to capture quantization effects better and speed up convergence. Extensive experiments show that QuantSR+ achieves state-of-the-art performance against both specialized quantized SR methods and generic quantization approaches. For SwinIR-S on Urban100 (x4), it improves PSNR by 0.29 dB over the 2-bit SOTA baseline. Meanwhile, it delivers strong efficiency gains at 2-bit, reducing operations by up to 87.9% and storage by 89.4%. QuantSR+ is effective for both convolutional and transformer-based SR models, indicating broad applicability.

Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may discard benefits associated with centering. This paper propose a framework to determine whether an LN in an arbitrary DNN can be replaced by RMSNorm without changing the model function. The key idea is to fold LN's centering operation into upstream general linear layers by enforcing zero-mean outputs through the column-centered constraint (CCC) and column-based weight centering (CBWC). We extend the analysis to arbitrary DNNs, define such LNs as foldable LNs, and develop a graph-based detection algorithm. Our analysis shows that many LNs in widely used architectures are foldable, enabling exact inference-time conversion and end-to-end acceleration of 2% to 12% without changing model predictions. Experiments across multiple task families further show that, when exact equivalence is partially broken in practical training settings, our method remains competitive with vanilla LN while improving efficiency.

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.

Time-Aware Adaptive Side Information Fusion for Sequential Recommendation

Incorporating item-side information, such as category and brand, into sequential recommendation is a well-established and effective approach for improving performance. However, despite significant advancements, current models are generally limited by three key challenges: they often overlook the fine-grained temporal dynamics inherent in timestamps, exhibit vulnerability to noise in user interaction sequences, and rely on computationally expensive fusion architectures. To systematically address these challenges, we propose the Time-Aware Adaptive Side Information Fusion (TASIF) framework. TASIF integrates three synergistic components: (1) a simple, plug-and-play time span partitioning mechanism to capture global temporal patterns; (2) an adaptive frequency filter that leverages a learnable gate to denoise feature sequences adaptively, thereby providing higher-quality inputs for subsequent fusion modules; and (3) an efficient adaptive side information fusion layer, this layer employs a "guide-not-mix" architecture, where attributes guide the attention mechanism without being mixed into the content-representing item embeddings, ensuring deep interaction while ensuring computational efficiency. Extensive experiments on four public datasets demonstrate that TASIF significantly outperforms state-of-the-art baselines while maintaining excellent efficiency in training. Our source code is available at https://github.com/jluo00/TASIF.

Mip-NeWRF: Enhanced Wireless Radiance Field with Hybrid Encoding for Channel Prediction

Recent work on wireless radiance fields represents a promising deep learning approach for channel prediction, however, in complex environments these methods still exhibit limited robustness, slow convergence, and modest accuracy due to insufficiently refined modeling. To address this issue, we propose Mip-NeWRF, a physics-informed neural framework for accurate indoor channel prediction based on sparse channel measurements. The framework operates in a ray-based pipeline with coarse-to-fine importance sampling: frustum samples are encoded, processed by a shared multilayer perceptron (MLP), and the outputs are synthesized into the channel frequency response (CFR). Prior to MLP input, Mip-NeWRF performs conical-frustum sampling and applies a scale-consistent hybrid positional encoding to each frustum. The scale-consistent normalization aligns positional encodings across scene scales, while the hybrid encoding supplies both scale-robust, low-frequency stability to accelerate convergence and fine spatial detail to improve accuracy. During training, a curriculum learning schedule is applied to stabilize and accelerate convergence of the shared MLP. During channel synthesis, the MLP outputs, including predicted virtual transmitter presence probabilities and amplitudes, are combined with modeled pathloss and surface interaction attenuation to enhance physical fidelity and further improve accuracy. Simulation results demonstrate the effectiveness of the proposed approach: in typical scenarios, the normalized mean square error (NMSE) is reduced by 14.3 dB versus state-of-the-art baselines.

Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning

Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose compromise would most severely degrade overall performance. In this paper, we study this Vulnerable Agent Identification (VAI) problem in large-scale multi-agent reinforcement learning (MARL). We frame VAI as a Hierarchical Adversarial Decentralized Mean Field Control (HAD-MFC), where the upper level involves an NP-hard combinatorial task of selecting the most vulnerable agents, and the lower level learns worst-case adversarial policies for these agents using mean-field MARL. The two problems are coupled together, making HAD-MFC difficult to solve. To solve this, we first decouple the hierarchical process by Fenchel-Rockafellar transform, resulting a regularized mean-field Bellman operator for upper level that enables independent learning at each level, thus reducing computational complexity. We then reformulate the upper-level combinatorial problem as a MDP with dense rewards from our regularized mean-field Bellman operator, enabling us to sequentially identify the most vulnerable agents by greedy and RL algorithms. This decomposition provably preserves the optimal solution of the original HAD-MFC. Experiments show our method effectively identifies more vulnerable agents in large-scale MARL and the rule-based system, fooling system into worse failures, and learns a value function that reveals the vulnerability of each agent.

Symmetry-Guided Multi-Agent Inverse Reinforcement Learning

In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement Learning (IRL) addresses this problem by inferring implicit reward functions from expert demonstrations. Nevertheless, existing methods rely heavily on large amounts of expert demonstrations to accurately recover the reward function. The high cost of collecting expert demonstrations in robotic applications, particularly in multi-robot systems, severely hinders the practical deployment of IRL. Consequently, improving sample efficiency has emerged as a critical challenge in multi-agent inverse reinforcement learning (MIRL). Inspired by the symmetry inherent in multi-agent systems, this work theoretically demonstrates that leveraging symmetry enables the recovery of more accurate reward functions. Building upon this insight, we propose a universal framework that integrates symmetry into existing multi-agent adversarial IRL algorithms, thereby significantly enhancing sample efficiency. Experimental results from multiple challenging tasks have demonstrated the effectiveness of this framework. Further validation in physical multi-robot systems has shown the practicality of our method.

Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video

We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to rasterization-based engines, while skeletal methods demand significant manual effort and lack cross-category generalization. Animating existing 3D assets, instead of creating 4D assets from scratch, demands a deep understanding of the input's 3D structure. To tackle these challenges, we present a 4D diffusion model that denoises sequences of latent sets, which are then decoded to produce mesh animations from point cloud trajectory sequences. These latent sets leverage a transformer-based variational autoencoder, simultaneously capturing 3D shape and motion information. By employing a spatiotemporal, transformer-based diffusion model, information is exchanged across multiple latent frames, enhancing the efficiency and generalization of the generated results. Our experimental results demonstrate that DriveAnyMesh can rapidly produce high-quality animations for complex motions and is compatible with modern rendering engines. This method holds potential for applications in both the gaming and filming industries.

VoQA: Visual-only Question Answering

We propose Visual-only Question Answering (VoQA), a novel multimodal task in which questions are visually embedded within images, without any accompanying textual input. This requires models to locate, recognize, and reason over visually embedded textual questions, posing challenges for existing large vision-language models (LVLMs), which show notable performance drops even with carefully designed prompts. To bridge this gap, we introduce Guided Response Triggering Supervised Fine-tuning (GRT-SFT), a structured fine-tuning strategy that guides the model to perform step-by-step reasoning purely based on visual input, significantly improving model performance. Our work enhances models' capacity for human-like visual understanding in complex multimodal scenarios, where information, including language, is perceived visually.

Enhancing the Efficiency of Complex Systems Crystal Structure Prediction by Active Learning Guided Machine Learning Potential

Understanding multicomponent complex material systems is essential for design of advanced materials for a wide range of technological applications. While state-of-the-art crystal structure prediction (CSP) methods effectively identify new structures and assess phase stability, they face fundamental limitations when applied to complex systems. This challenge stems from the combinatorial explosion of atomic configurations and the vast stoichiometric space, both of which contribute to computational demands that rapidly exceed practical feasibility. In this work, we propose a flexible and automated workflow to build a highly generalizable and data-efficient machine learning potential (MLP), effectively unlocking the full potential of CSP algorithms. The workflow is validated on both Mg-Ca-H ternary and Be-P-N-O quaternary systems, demonstrating substantial machine learning acceleration in high-throughput structural optimization and enabling the efficient identification of promising compounds. These results underscore the effectiveness of our approach in exploring complex material systems and accelerating the discovery of new multicomponent materials.