论文检索

Computer Vision · Everything Else

Robin Courant, Xi WANG, David Loiseaux, Marc Christie, Vicky Kalogeiton

Treating human motion and camera trajectory generation separately overlooks a core principle of cinematography: the tight interplay between actor performance and camera work in the screen space. In this paper, we are the first to cast this task as a text-conditioned joint generation, aiming to maintain consistent on-screen framing while producing two heterogeneous, yet intrinsically linked, modalities: human motion and camera trajectories. We propose a simple, model-agnostic framework that enforces multimodal coherence via an auxiliary modality: the on-screen framing induced by projecting human joints onto the camera. This on-screen framing provides a natural and effective bridge between modalities, promoting consistency and leading to more precise joint distribution. We first design a joint autoencoder that learns a shared latent space, together with a lightweight linear mapping from the human and camera latents to a framing latent. We then introduce Auxiliary Sampling, which exploits this linear map to steer generation toward a coherent framing modality. To support this task, we also introduce the PulpMotion dataset, a camera-motion and human-motion dataset with rich captions, and high-quality human motions. Extensive experiments across DiT- and MAR-based architectures show the generality and effectiveness of our method in generating on-frame coherent camera-human motions, while also achieving gains on textual alignment for both modalities. Our qualitative results yield more cinematographically meaningful framings setting the new state of the art for this task.

Deep Learning · Everything Else

Makram Chahine, Philipp Nazari, Daniela Rus, T. Konstantin Rusch

State Space Models (SSMs), developed to tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference. At their core are recurrent dynamical systems that maintain a hidden state, with update costs scaling with the state dimension. A key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden. Control theory, and more specifically Hankel singular value analysis, provides a potent framework for the measure of energy for each state, as well as the balanced truncation of the original system down to a smaller representation with performance guarantees. Leveraging the eigenvalue stability properties of Hankel matrices, we apply this lens to SSMs $\textit{during training}$, where only dimensions of high influence are identified and preserved. Our approach, CompreSSM, applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models. Experiments show that in-training reduction significantly accelerates optimization while preserving expressivity, with compressed models retaining task-critical structure lost by models trained directly at smaller dimension. In other words, SSMs that begin large and shrink during training achieve computational efficiency while maintaining higher performance. Project code is available at https://github.com/camail-official/compressm.

Reinforcement Learning · Everything Else

Julian Quevedo, Ansh Kumar Sharma, Yixiang Sun, Varad Suryavanshi, Percy Liang, Sherry Yang

Evaluating robot control policies is difficult: real-world testing is costly, and handcrafted simulators require manual effort to improve in realism and generality. We propose a world-model-based policy evaluation environment (WorldGym), an autoregressive, action-conditioned video generation model which serves as a proxy to real world environments. Policies are evaluated via Monte Carlo rollouts in the world model, with a vision-language model providing rewards. We evaluate a set of VLA-based real-robot policies in the world model using only initial frames from real robots, and show that policy success rates within the world model highly correlate with real-world success rates. Moreoever, we show that WorldGym is able to preserve relative policy rankings across different policy versions, sizes, and training checkpoints. Due to requiring only a single start frame as input, the world model further enables efficient evaluation of robot policies' generalization ability on novel tasks and environments. We find that modern VLA-based robot policies still struggle to distinguish object shapes and can become distracted by adversarial facades of objects. While generating highly realistic object interaction remains challenging, WorldGym faithfully emulates robot motions and offers a practical starting point for safe and reproducible policy evaluation before deployment.

Deep Learning · Everything Else

Hyunwoo Kim, BYOUNGCHAN KO, Minseok Kang, Minwoo Kim, Dongjin Lee, Jaehoon Lee, Sungroh Yoon, Dahuin Jung

Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providing a viable alternative to Transformers. Building upon this, Mamba-2 introduces the Structured State Space Duality (SSD), which integrates recurrent and attention modes to achieve efficiency and scalability. However, this architectural expansion substantially increases memory and latency overhead, underscoring the need for efficient compression strategies tailored to SSD. In this work, we present SSDi8, the first post-training quantization framework specifically designed for SSD to maintain a persistent INT8 path. SSDi8 introduces a reformulation that decouples element-wise multiplications from matrix multiplications, enabling reuse of quantized activations across modules. Moreover, SSDi8 adaptively quantizes channel-varying activations at cost-effective points, further reducing latency. On the accuracy side, SSDi8 explicitly leverages the intrinsic dimensional decomposition of SSD, exploiting distinct outlier distributions across axes, and incorporates an error correction term based on per-channel error statistics. Comprehensive experiments demonstrate that SSDi8 achieves accuracy comparable to FP16 while delivering up to 1.4X speedup in W4A8 and W8A8 settings. We further validate its robustness in resource-constrained environments by deploying it on the Orin NX device. Code is available at https://github.com/cau-hai-lab/SSDi8.

Computer Vision · Everything Else

Song Fei, Tian Ye, Lujia Wang, Lei Zhu

Universal image restoration (UIR) aims to recover images degraded by unknown mixtures while preserving semantics—conditions under which discriminative restorers and UNet-based diffusion priors often oversmooth, hallucinate, or drift. We present LucidFlux, a caption-free UIR framework that adapts a large diffusion transformer (Flux.1) to restoration with minimal parameter overhead. LucidFlux introduces a lightweight \emph{dual-branch conditioner} that injects signals from the degraded input and a lightly restored proxy to respectively anchor geometry and suppress artifacts. A timestep- and layer-adaptive modulation schedule routes these cues across the backbone’s hierarchy, yielding coarse-to-fine, context-aware updates that protect global structure while recovering texture. To avoid the latency and instability of text prompts or VLM captions, we enforce \emph{caption-free semantic alignment} via SigLIP features extracted from the proxy. A scalable curation pipeline further filters large-scale data for structure-rich supervision. Across synthetic and in-the-wild benchmarks, LucidFlux consistently surpasses strong open-source and commercial baselines across seven metrics, with clear visual gains in realism, detail, and artifact suppression. Ablations confirm that, for large DiTs, when, where, and what to condition—rather than scaling parameters or relying on text prompts—is the key lever for robust, prompt-free restoration.

Applications · Everything Else

Gust Verbruggen, Chris Parnin, Vu Le, Sumit Gulwani

We introduce jqBench, a new benchmark for evaluating language models on JSON querying and transformation tasks, where the intent can be given specified using natural language and/or examples. Whereas jqBench is mainly aimed at using the jq tool, it can be used to evaluate other programming languages that query and/or transform JSON. Benchmarks are automatically created from two rich sources of data: Stack Overflow discussions (1496 instances with instructions and examples, called jqStack) and the Spider dataset for SQL generation from natural language (859 instances with instructions and JSON Schema, called jqSpider). We describe and analyze the automated pipeline for benchmark creation, and perform extensive baseline experiments on different models to analyze the complexity and failure modes. Using implicit feedback, the best model (Opus 4.1) scores 76% on the jqStack benchmarks and 81% on the jqSpider benchmarks. Additionally, we show (1) that access to the documentation surprisingly does not help, (2) jq lags behind Python, and (3) that automatic feedback (and therefore examples) is crucial. Besides the challenging benchmarks, we release 13K converted but filtered cases for training purposes.

Reinforcement Learning · Everything Else

Yuqian Fu, Tinghong Chen, Jiajun Chai, Xihuai Wang, Songjun Tu, Guojun Yin, Wei Lin, Qichao Zhang, Yuanheng Zhu, Dongbin Zhao

Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet optimally integrating Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remains a fundamental challenge. Through a comprehensive analysis of token distributions, learning dynamics, and integration mechanisms from an entropy-based perspective, we reveal key differences between these paradigms: SFT induces coarse-grained, global shifts to policy distributions, while RL performs fine-grained, selective optimizations. Our analysis further establishes entropy as a critical indicator of training efficacy. Building on these observations, we introduce **S**upervised **R**einforcement **F**ine-**T**uning (**SRFT**), a single-stage framework that unifies both fine-tuning paradigms through entropy-aware weighting mechanisms. SRFT simultaneously applies SFT and RL to directly optimize LLMs using demonstrations and self-exploration rollouts rather than through two-stage sequential methods. Extensive experiments show that SRFT outperforms zero-RL baselines by **9.0%** on five mathematical reasoning benchmarks and by **10.9%** on three out-of-distribution benchmarks. Moreover, by leveraging demonstration data, SRFT maintains a more stable policy entropy, facilitating sustained policy improvement.

Deep Learning · Everything Else

Or Tal, Felix Kreuk, Yossi Adi

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ significantly in many dimensions, such as training datasets, modeling paradigms, and architectural choices. This diversity complicates efforts to evaluate models fairly and identify which design choices influence performance the most. While factors like data and architecture are important, in this study we focus exclusively on the modeling paradigm. We conduct a systematic empirical analysis to isolate its effects, offering insights into associated trade-offs and emergent behaviors that can guide future text-to-music generation systems. Specifically, we compare the two arguably most common modeling paradigms: auto-regressive decoding and conditional flow-matching. We conduct a controlled comparison by training all models from scratch using identical datasets, training configurations, and similar backbone architectures. Performance is evaluated across multiple axes, including generation quality, robustness to inference configurations, scalability, adherence to both textual and temporally aligned conditioning, and editing capabilities in the form of audio inpainting. This comparative study sheds light on distinct strengths and limitations of each paradigm, providing actionable insights that can inform future architectural and training decisions in the evolving landscape of text-to-music generation. Audio sampled examples are available at: https://huggingface.co/spaces/ortal1602/ARvsFM

Deep Learning · Everything Else

Abhranil Chandra, Sreevatsa Muppirala, Manish Gupta, Pawan Goyal

Assessing the quality of generative model outputs from large language models (LLMs) or vision-language models (VLMs), poses significant challenges. Traditional evaluation methods either rely on human assessment which is resource-intensive and not scalable or on automatic metrics that often correlate poorly with human preferences. Another approach is to train dedicated neural evaluators, but this typically requires substantial training data and compute. In this study, we thus introduce ReFeR, a tuning-free framework for evaluating generative outputs including both text and images, using a two-level hierarchy of pre-trained LLM and VLM evaluators. This multi-agent hierarchical strategy leverages additional compute at inference time by orchestrating multiple models and utilizing the increased test-time reasoning to boost performance. By having models themselves provide feedback and final judgments, ReFeR reduces the dependence on human evaluation. We rigorously evaluate ReFeR on four diverse evaluation benchmarks, where it surpasses prior methods in accuracy while also generating constructive feedback useful for downstream distillation and self-improvement via finetuning. Interestingly, ReFeR is also applicable for reasoning tasks - experiments on four reasoning benchmarks show ReFeR’s superior collective reasoning abilities. We present two variants of the framework: ReFeR-Turbo, optimized for accelerated performance, and ReFeR-Lite, offering a more test-time compute efficient solution. ReFeR-Lite is $\sim12-14\times$ more compute efficient than previous works while being comparably accurate to ReFeR-Turbo.

General Machine Learning · Everything Else

Asher Labovich

Modern Gradient Boosted Decision Trees (GBDTs) accelerate split finding with histogram-based binning, which reduces complexity from $O(N\log N)$ to $O(N)$ by aggregating gradients into fixed-size bins. However, the predominant quantile binning strategy—designed to distribute data points evenly among bins—may overlook critical boundary values that could enhance predictive performance. In this work, we consider a novel approach that replaces quantile binning with a $k$-means discretizer initialized with quantile bins, and justify the swap with a proof showing how, for any $L$-Lipschitz function, k-means maximizes the worst-case explained variance of Y obtained when treating all values in a given bin as equivalent. We test this swap against quantile and uniform binning on 33 OpenML datasets plus synthetics that control for modality, skew, and bin budget. Across 18 regression datasets, k-means shows no statistically significant losses at the 5% level and wins in three cases—most strikingly a 55% MSE drop on one particularly skewed dataset—even though k-means' mean reciprocal rank (MRR) is slightly lower (0.65 vs 0.72). On the 15 classification datasets the two methods are statistically tied (MRR 0.70 vs 0.68) with gaps $\leq$0.2 pp. Synthetic experiments confirm consistently large MSE gains—typically $>$20% and rising to 90% as outlier magnitude increases or bin budget drops. We find that k-means keeps error on par with exhaustive (no-binning) splitting when extra cuts add little value, yet still recovers key split points that quantile overlooks. As such, we advocate for a built-in bin_method=$k$-means flag, especially in regression tasks and in tight-budget settings such as the 32–64-bin GPU regime—because it is a "safe default" with large upside, yet adds only a one-off, cacheable overhead ($\approx$ 3.5s per feature to bin 10M rows on one Apple M1 thread).

General Machine Learning · Everything Else

Qiuyi Chen, Haiyang Zhang, Leqi Zhang, Changchun Li, Jia Wang, Wei Wang

Positive-Unlabeled (PU) learning, a challenging paradigm for training binary classifiers from only positive and unlabeled samples, is fundamental to many applications. While numerous PU learning methods have been proposed, the research is systematically hindered by the lack of a standardized and comprehensive benchmark for rigorous evaluation. Inconsistent data generation, disparate experimental settings, and divergent metrics have led to irreproducible findings and unsubstantiated performance claims. To address this foundational challenge, we introduce **PU-Bench**, the first unified open-source benchmark for PU learning. PU-Bench provides: 1) a unified data generation pipeline to ensure consistent input across configurable sampling schemes, label ratios and labeling mechanisms; 2) an integrated framework of 18 state-of-the-art PU methods; and 3) standardized protocols for reproducible assessment. Through a large-scale empirical study on 8 diverse datasets (**2880** evaluations in total), PU-Bench reveals a complex yet intuitive performance landscape, uncovering critical trade-offs between effectiveness and efficiency, and systematically mapping method robustness against variations in label frequency and selection bias. It is anticipated to serve as a foundational resource to catalyze reproducible, rigorous, and impactful research in the PU learning community. The source code is publicly available at .

Deep Learning · Everything Else

Renat Sergazinov, Shao-An Yin

Tabular foundation models struggle with large datasets due to the quadratic attention. While methods like FlashAttention promise scalability, practical challenges persist in their application to tabular foundation models. Our work resolves these hurdles, enabling efficient attention, and reveals that contrary to the eariler reports, TabPFN's performance improves with larger contexts, highlighting its inherent robustness and minimal fine-tuning needs when scaling to complex, long datasets from the TabArena benchmark.

Deep Learning · Everything Else

XIAODIE YI, Hayun Lee, Dongkun Shin

N:M sparsity has emerged as a hardware-friendly pruning strategy, notably supported by NVIDIA’s Sparse Tensor Cores. While efficient, its fixed sparsity ratio restricts flexibility, making it difficult to adapt pruning granularity to varying weight importance across layers and architectures. To overcome this limitation, we propose FlexHiNM, a hybrid framework that adaptively partitions each layer into three regions: dense, vector-pruned, and N:M sparse, enabling finer-grained control while preserving hardware compatibility. To better preserve salient weights, we extend this to FlexHiNM-GP, which incorporates Gyro-Permutation, an iterative channel-rearrangement algorithm. Through successive sampling, clustering, and assignment, Gyro-Permutation aligns high-importance weights with structured sparsity patterns and mitigates suboptimal configurations in multi-level pruning. During gradual pruning, FlexHiNM-GP further employs a differentiable masking mechanism based on the Hard Concrete distribution, enabling gradient-based mask learning and preventing over-aggressive early pruning. Experiments on vision and language benchmarks demonstrate that FlexHiNM-GP consistently surpasses strong structured baselines and approaches the performance of unstructured pruning, validating the effectiveness of combining hybrid sparsity with learned masks and permutation strategies.

Deep Learning · Everything Else

Sanghyun Lee, Hoh In

Aligning Large Language Models with human preferences typically requires computationally intensive training or complex reward architectures. We introduce PALC (Preference Alignment via Logit Calibration), a parameter-efficient framework that achieves test-time alignment through a novel intervention strategy: direct calibration in vocabulary space. Unlike existing methods that manipulate entangled hidden representations or rely on external reward models, PALC operates at the logit layer where each dimension corresponds to a distinct token, providing interpretable and efficient control. Our approach employs a bottleneck architecture that learns to compress the base model's hidden states and generate position-dependent calibration vectors, requiring only a fraction of the base model's parameters. Through this design, PALC sidesteps the superposition problem inherent in representation engineering while eliminating the computational overhead of guided decoding methods. A single scaling factor enables runtime adjustment of alignment strength without retraining, allowing practitioners to balance between preserving model capabilities and enforcing preferences. Experiments demonstrate that PALC outperforms most test-time alignment methods while maintaining near-baseline inference speed. Our ablations reveal that human preferences concentrate on surprisingly low-dimensional manifolds, validating our architectural choices. By establishing vocabulary-space intervention as an effective alignment paradigm, PALC makes preference alignment accessible for resource-constrained deployments where traditional methods are infeasible, opening new avenues for scalable and adaptive AI alignment.

General Machine Learning · Everything Else

Wenxing Zhou, Timothy Cannings

We introduce a new, flexible, and theoretically justified framework for dimension reduction in high-dimensional regression, based on an ensemble of random projections. Specifically, we consider disjoint groups of independent random projections, retain the best projection in each group according to the empirical regression performance on the projected covariates, and then aggregate the selected projections via singular value decomposition. The singular values quantify the relative importance of corresponding projection directions and guide the dimension selection process. We investigate various aspects of our framework, including the choice of projection distribution and the number of projections used. Our theoretical results show that the expected estimation error decreases as the number of groups of projections increases. Finally, we demonstrate that our proposal consistently matches or outperforms state-of-the-art methods through extensive numerical studies on simulated and real data.

Applications · Everything Else

Md Ahsanul Haque, Ismail Hossain, Mahmuduzzaman Kamol, Jahangir Alam, Suresh Kumar Amalapuram, Sajedul Talukder, Mohammad Saidur Rahman

Machine learning (ML)-based malware detection systems often fail to account for the dynamic nature of real-world training and test data distributions. In practice, these distributions evolve due to frequent changes in the Android ecosystem, adversarial development of new malware families, and the continuous emergence of both benign and malicious applications. Prior studies have shown that such concept drift—distributional shifts in benign and malicious samples, leads to significant degradation in detection performance over time. Despite the practical importance of this issue, existing datasets are often outdated and limited in temporal scope, diversity of malware families, and sample scale, making them insufficient for the systematic evaluation of concept drift in malware detection. To address this gap, we present LAMDA, the largest and most temporally diverse Android malware benchmark to date, designed specifically for concept drift analysis. LAMDA spans 12 years (2013–2025, excluding 2015), includes over 1 million samples (approximately 37\% labeled as malware), and covers 1,380 malware families and 150,000 singleton samples, reflecting the natural distribution and evolution of real-world Android applications. We empirically demonstrate LAMDA's utility by quantifying the performance degradation of standard ML models over time and analyzing feature stability across years. As the most comprehensive Android malware dataset to date, LAMDA enables in-depth research into temporal drift, generalization, explainability, and evolving detection challenges.

General Machine Learning · Everything Else

Ronaldinho Vega Centeno Olivera, Allan M. de Souza, JULIO DOS REIS, Mateus da Silveira, Alejandro Núñez Arroyo

The scalability and robustness of current Multi-Agent Systems (MAS) are severely constrained by the heterogeneity of communication interfaces and a reliance on fragile ad-hoc integrations. We introduce FRACTAL-MAS, a recursive architecture that standardizes orchestration through the convergence of MCP and A2A protocols, integrating a unified control loop with procedural memory grounded in Case-Based Reasoning (CBR). This design allows for continuous adaptation without fine-tuning and enables a seamless transition from rigid hierarchical structures to decentralized networks, providing a reference architecture for the robust and scalable construction of MAS.

Deep Learning · Everything Else

Guanhua Zhang, Ricardo Dominguez-Olmedo, Moritz Hardt

Existing language model benchmarks provide contradictory model rankings, even for benchmarks that aim to capture similar skills. This dilemma of conflicting rankings hampers model selection, clouds model comparisons, and adds confusion to a growing ecosystem of competing models. In this paper, we take a different perspective on model comparison: instead of relying on out-of-the-box performance via direct evaluation, we compare model potential by providing each model with identical benchmark-specific fine-tuning before evaluation. We call this approach train-before-test. Our primary contribution is a comprehensive empirical evaluation of model potential across 24 benchmarks and 61 models. First, we demonstrate that model potential rankings obtained through train-before-test exhibit remarkable consistency across all benchmarks. Whereas traditional rankings demonstrate little external validity under direct evaluation, they enjoy a significant degree of external validity when applying train-before-test: model potential rankings transfer gracefully from one benchmark to another. Second, train-before-test restores the connection between perplexity and downstream task performance, lost under direct evaluation. Remarkably, even pre-finetuning perplexity of a base model predicts post-finetuning downstream performance, suggesting that ranking consistency reflects inherent model potential rather than fine-tuning artifacts. Finally, train-before-test reduces the model-score matrix to essentially rank one, indicating that model potential is dominated by one latent factor, uncovered by train-before-test. While direct evaluation remains useful for assessing deployment-ready performance, train-before-test provides a complementary lens for understanding achievable performance of models after adaptation.

Applications · Everything Else

Junlong Li, Wenshuo Zhao, Jian Zhao, Weihao Zeng, Haoze Wu, Xiaochen Wang, Rui Ge, Yuxuan Cao, Yuzhen Huang, Wei Liu 等

Real-world language agents must handle complex, multi-step workflows across diverse applications. For instance, an agent may manage emails by coordinating with calendars and file systems, or monitor a production database like BigQuery to detect anomalies and generate reports following a standard operating manual. However, existing language agent benchmarks often focus on narrow domains or simplified tasks that lack the diversity, realism, and long-horizon complexity required to evaluate agents' real-world performance. To address this gap, we introduce the Tool Decathlon (dubbed as Toolathlon), a benchmark for language agents offering diverse applications and tools, realistic environment setup, and reliable execution-based evaluation. Toolathlon spans 32 software applications and 604 tools, ranging from everyday platforms such as Google Calendar and Notion to professional applications like WooCommerce, Kubernetes, and BigQuery. Most of the tools are based on a high-quality set of Model Context Protocol (MCP) servers that we may have revised or implemented ourselves. Unlike prior works, which primarily ensure functional realism but offer limited environment state diversity, we provide realistic initial environment states from real software, such as Canvas courses with dozens of students or real-world financial spreadsheets. The Toolathlon benchmark includes 108 manually sourced or crafted tasks in total, requiring interacting with multiple applications over around 20 turns on average to complete. Each task is strictly verifiable through dedicated evaluation scripts. Comprehensive evaluation of state-of-the-art models highlights their significant shortcomings in performing real-world, long-horizon tasks: the best-performing model, Claude-4.5-Sonnet, achieves only a 38.6% success rate with 20.2 tool calling turns on average, while the top open-weights model DeepSeek-V3.2-Exp reaches 20.1%. We expect Toolathlon to drive the development of more capable language agents for real-world, long-horizon task execution.

Reinforcement Learning · Everything Else

KaShun SHUM, Binyuan Hui, Jiawei Chen, Lei Zhang, X. W., Jiaxi Yang, Yuzhen Huang, Junyang Lin, Junxian He

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to provide accurate feedback, and the resulting feedback is often sparse and cannot effectively distinguish between trajectories that are both successful or both unsuccessful. In contrast, execution-free feedback from reward models can provide more fine-grained signals without depending on unit test cases. Despite this potential, execution-free feedback for realistic software engineering (SWE) agents remains underexplored. Aiming to develop versatile reward models that are effective across TTS and RL, however, we observe that two verifiers with nearly identical TTS performance can nevertheless yield very different results in RL. Intuitively, TTS primarily reflects the model’s ability to select the best trajectory, but this ability does not necessarily generalize to RL. To address this limitation, we identify two additional aspects that are crucial for RL training: classification accuracy and calibration. We then conduct comprehensive controlled experiments to investigate how to train a robust reward model that performs well across these metrics. In particular, we analyze the impact of various factors such as training data scale, policy mixtures, and data source composition. Guided by these investigations, we introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference. SWE-RM substantially improves SWE agents on both TTS and RL performance. For example, it increases the accuracy of Qwen3-Coder-Flash from 51.6% to 62.0%, and Qwen3-Coder-Max from 67.0% to 74.6% on SWE-Bench Verified using TTS, achieving new state-of-the-art performance among open-source models. On RL training, SWE-RM lifts the resolve rate of execution-based counterparts by 3 absolute points on SWE-Bench Verified.