VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation

Screenshot-to-code generation aims to translate user interface screenshots into executable frontend code that faithfully reproduces the target layout and style. Existing multimodal large language models perform this mapping directly from screenshots but are trained without observing the visual outcomes of their generated code. In contrast, human developers iteratively render their implementation, compare it with the design, and learn how visual differences relate to code changes. Inspired by this process, we propose VisRefiner, a training framework that enables models to learn from visual differences between rendered predictions and reference designs. We construct difference-aligned supervision that associates visual discrepancies with corresponding code edits, allowing the model to understand how appearance variations arise from implementation changes. Building on this, we introduce a reinforcement learning stage for self-refinement, where the model improves its generated code by observing both the rendered output and the target design, identifying their visual differences, and updating the code accordingly. Experiments show that VisRefiner substantially improves single-step generation quality and layout fidelity, while also endowing models with strong self-refinement ability. These results demonstrate the effectiveness of learning from visual differences for advancing screenshot-to-code generation.

OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions

The rapid advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primarily adopt a deductive paradigm, where agents execute tasks based on explicitly provided rules and static goals, often within limited planning horizons. Crucially, this neglects the inductive necessity for agents to discover latent transition laws from experience autonomously, which is the cornerstone for enabling agentic foresight and sustaining strategic coherence. To bridge this gap, we introduce OdysseyArena, which re-centers agent evaluation on long-horizon, active, and inductive interactions. We formalize and instantiate four primitives, translating abstract transition dynamics into concrete interactive environments. Building upon this, we establish OdysseyArena-Lite for standardized benchmarking, providing a set of 120 tasks to measure an agent's inductive efficiency and long-horizon discovery. Pushing further, we introduce OdysseyArena-Challenge to stress-test agent stability across extreme interaction horizons (e.g., > 200 steps). Extensive experiments on 15+ leading LLMs reveal that even frontier models exhibit a deficiency in inductive scenarios, identifying a critical bottleneck in the pursuit of autonomous discovery in complex environments. Our code and data are available at https://github.com/xufangzhi/Odyssey-Arena

From Bench to Flight: Translating Drone Impact Tests into Operational Safety Limits

Indoor micro-aerial vehicles (MAVs) are increasingly used for tasks that require close proximity to people, yet practitioners lack practical methods to tune motion limits based on measured impact risk. We present an end-to-end, open toolchain that converts benchtop impact tests into deployable safety governors for drones. First, we describe a compact and replicable impact rig and protocol for capturing force-time profiles across drone classes and contact surfaces. Second, we provide data-driven models that map pre-impact speed to impulse and contact duration, enabling direct computation of speed bounds for a target force limit. Third, we release scripts and a ROS2 node that enforce these bounds online and log compliance, with support for facility-specific policies. We validate the workflow on multiple commercial off-the-shelf quadrotors and representative indoor assets, demonstrating that the derived governors preserve task throughput while meeting force constraints specified by safety stakeholders. Our contribution is a practical bridge from measured impacts to runtime limits, with shareable datasets, code, and a repeatable process that teams can adopt to certify indoor MAV operations near humans.

Efficient Estimation of Kernel Surrogate Models for Task Attribution

Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text prediction -- simultaneously. A key question is to quantify how each individual training task influences performance on a target task, a problem we refer to as task attribution. The direct approach, leave-one-out retraining, measures the effect of removing each task, but is computationally infeasible at scale. An alternative approach that builds surrogate models to predict a target task's performance for any subset of training tasks has emerged in recent literature. Prior work focuses on linear surrogate models, which capture first-order relationships, but miss nonlinear interactions such as synergy, antagonism, or XOR-type effects. In this paper, we first consider a unified task weighting framework for analyzing task attribution methods, and show a new connection between linear surrogate models and influence functions through a second-order analysis. Then, we introduce kernel surrogate models, which more effectively represent second-order task interactions. To efficiently learn the kernel surrogate, we develop a gradient-based estimation procedure that leverages a first-order approximation of pretrained models; empirically, this yields accurate estimates with less than $2\%$ relative error without repeated retraining. Experiments across multiple domains -- including math reasoning in transformers, in-context learning, and multi-objective reinforcement learning -- demonstrate the effectiveness of kernel surrogate models. They achieve a $25\%$ higher correlation with the leave-one-out ground truth than linear surrogates and influence-function baselines. When used for downstream task selection, kernel surrogate models yield a $40\%$ improvement in demonstration selection for in-context learning and multi-objective reinforcement learning benchmarks.

Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation

Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. Existing fine-tuned models tend to reactively follow user instructions and hallucinate dimensions when the text is ambiguous. To address this, we propose a proactive agentic framework for text-to-CadQuery generation, named ProCAD, that resolves specification issues before code synthesis. Our framework pairs a proactive clarifying agent, which audits the prompt and asks targeted clarification questions only when necessary to produce a self-consistent specification, with a CAD coding agent that translates the specification into an executable CadQuery program. We fine-tune the coding agent on a curated high-quality text-to-CadQuery dataset and train the clarifying agent via agentic SFT on clarification trajectories. Experiments show that proactive clarification significantly improves robustness to ambiguous prompts while keeping interaction overhead low. ProCAD outperforms frontier closed-source models, including Claude Sonnet 4.5, reducing the mean Chamfer distance by 79.9 percent and lowering the invalidity ratio from 4.8 percent to 0.9 percent. Our code and datasets will be made publicly available.

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to only generate frontend web pages, masking the lack of real full-stack data processing and storage with fancy visual effects. Notably, constructing production-level full-stack web applications is far more challenging than only generating frontend web pages, demanding careful control of data flow, comprehensive understanding of constantly updating packages and dependencies, and accurate localization of obscure bugs in the codebase. To address these difficulties, we introduce FullStack-Agent, a unified agent system for full-stack agentic coding that consists of three parts: (1) FullStack-Dev, a multi-agent framework with strong planning, code editing, codebase navigation, and bug localization abilities. (2) FullStack-Learn, an innovative data-scaling and self-improving method that back-translates crawled and synthesized website repositories to improve the backbone LLM of FullStack-Dev. (3) FullStack-Bench, a comprehensive benchmark that systematically tests the frontend, backend and database functionalities of the generated website. Our FullStack-Dev outperforms the previous state-of-the-art method by 8.7%, 38.2%, and 15.9% on the frontend, backend, and database test cases respectively. Additionally, FullStack-Learn raises the performance of a 30B model by 9.7%, 9.5%, and 2.8% on the three sets of test cases through self-improvement, demonstrating the effectiveness of our approach. The code is released at https://github.com/mnluzimu/FullStack-Agent.

Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation

Semantic segmentation of high-resolution remote-sensing imagery is critical for urban mapping and land-cover monitoring, yet training data typically exhibits severe long-tailed pixel imbalance. In the dataset LoveDA, this challenge is compounded by an explicit Urban/Rural split with distinct appearance and inconsistent class-frequency statistics across domains. We present a prompt-controlled diffusion augmentation framework that synthesizes paired label--image samples with explicit control of both domain and semantic composition. Stage~A uses a domain-aware, masked ratio-conditioned discrete diffusion model to generate layouts that satisfy user-specified class-ratio targets while respecting learned co-occurrence structure. Stage~B translates layouts into photorealistic, domain-consistent images using Stable Diffusion with ControlNet guidance. Mixing the resulting ratio and domain-controlled synthetic pairs with real data yields consistent improvements across multiple segmentation backbones, with gains concentrated on minority classes and improved Urban and Rural generalization, demonstrating controllable augmentation as a practical mechanism to mitigate long-tail bias in remote-sensing segmentation. Source codes, pretrained models, and synthetic datasets are available at \href{https://github.com/Buddhi19/SyntheticGen.git}{Github}

Real-time processing of analog signals on accelerated neuromorphic hardware

Sensory processing with neuromorphic systems is typically done by using either event-based sensors or translating input signals to spikes before presenting them to the neuromorphic processor. Here, we offer an alternative approach: direct analog signal injection eliminates superfluous and power-intensive analog-to-digital and digital-to-analog conversions, making it particularly suitable for efficient near-sensor processing. We demonstrate this by using the accelerated BrainScaleS-2 mixed-signal neuromorphic research platform and interfacing it directly to microphones and a servo-motor-driven actuator. Utilizing BrainScaleS-2's 1000-fold acceleration factor, we employ a spiking neural network to transform interaural time differences into a spatial code and thereby predict the location of sound sources. Our primary contributions are the first demonstrations of direct, continuous-valued sensor data injection into the analog compute units of the BrainScaleS-2 ASIC, and actuator control using its embedded microprocessors. This enables a fully on-chip processing pipeline$\unicode{x2014}$from sensory input handling, via spiking neural network processing to physical action. We showcase this by programming the system to localize and align a servo motor with the spatial direction of transient noise peaks in real-time.

MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research

Operations Research (OR) relies on expert-driven modeling-a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing approaches either rely on costly post-training or employ multi-agent frameworks, yet most still lack reliable collaborative error correction and task-specific retrieval, often leading to incorrect outputs. We propose MIRROR, a fine-tuning-free, end-to-end multi-agent framework that directly translates natural language optimization problems into mathematical models and solver code. MIRROR integrates two core mechanisms: (1) execution-driven iterative adaptive revision for automatic error correction, and (2) hierarchical retrieval to fetch relevant modeling and coding exemplars from a carefully curated exemplar library. Experiments show that MIRROR outperforms existing methods on standard OR benchmarks, with notable results on complex industrial datasets such as IndustryOR and Mamo-ComplexLP. By combining precise external knowledge infusion with systematic error correction, MIRROR provides non-expert users with an efficient and reliable OR modeling solution, overcoming the fundamental limitations of general-purpose LLMs in expert optimization tasks.

QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization

The advent of Vision-Language-Action (VLA) models represents a significant leap for embodied intelligence, yet their immense computational demands critically hinder deployment on resource-constrained robotic platforms. Intuitively, low-bit quantization is a prevalent and preferred technique for large-scale model compression. However, we find that a systematic analysis of VLA model's quantization is fundamentally lacking. We argue that naively applying uniform-bit quantization from Large Language Models (LLMs) to robotics is flawed, as these methods prioritize passive data fidelity while ignoring how minor action deviations compound into catastrophic task failures. To bridge this gap, we introduce QVLA, the first action-centric quantization framework specifically designed for embodied control. In a sharp departure from the rigid, uniform-bit quantization of LLM-based methods, QVLA introduces a highly granular, channel-wise bit allocation strategy. Its core mechanism is to directly measure the final action-space sensitivity when quantizing each individual channel to various bit-widths. This process yields a precise, per-channel importance metric that guides a global optimization, which elegantly unifies quantization and pruning (0-bit) into a single, cohesive framework. Extensive evaluations on different baselines demonstrate the superiority of our approach. In the LIBERO, the quantization version of OpenVLA-OFT with our method requires only 29.2% of the original model's VRAM while maintaining 98.9% of its original performance and achieving a 1.49x speedup. This translates to a 22.6% performance improvement over the LLM-derived method SmoothQuant. Our work establishes a new, principled foundation for compressing VLA models in robotics, paving the way for deploying powerful, large-scale models on real-world hardware. Code will be released.