arXiv subjects

Yang Ye

Publications and source records attributed to Yang Ye.

At least 19 recordsLinked to original sources

arXiv2026

ASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination

Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL (MTRL) approach. However, existing MTRL methods treat all coding tasks uniformly, relying on fixed data curricula under a shared optimization strategy, ultimately limiting the effectiveness of multi-task training. To address these limitations, we propose ASTOR, a multi-tASk code reinforcement learning framework via uTility-driven coORdination. Centered on task utility, a signal capturing each task learning potential and cross-task synergy, ASTOR comprises two coupled modules: 1) Hierarchical Utility-Routed Data Scheduling module hierarchically allocates training budget and prioritizes informative prompts, steering training toward the most valuable data and 2) Adaptive Utility-Calibrated Policy Optimization module dynamically scales per-task KL regularization, matching update constraints to each tasks current training state. Experiments on two widely-used LLMs across four representative coding tasks demonstrate that ASTOR consistently improves a single model across all tasks, outperforming the best task-specific specialist by 9.0%-9.5% and surpassing the strongest MTRL baseline by 7.5%-12.8%.

cs.SE↗

arXiv2026

CuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data

Robot imitation learning uses demonstrations from operators of varying skill, but selecting training data remains challenging. Existing methods score demonstrations using smoothness, diversity, or estimated influence on policy performance, but differences in selection and evaluation protocols make it difficult to determine whether they outperform simple baselines. We introduce \textbf{CuraEval}, a framework combining mathematical analysis of demonstration scores with controlled comparisons against fixed size-matched random subsets and full-data training on mixed-skill robomimic data using Diffusion Policy and BC-RNN. We show that the evaluated PSD score depends only on episode length and squared position magnitudes, and produces nearly the same ranking as episode length on \textit{square} ($ρ=0.999$). With Diffusion Policy, selecting the shortest 50\% of demonstrations improves \textit{square} success from 70.7\% under random selection to 76.5\%. Compared with random selection, our adapted geometric-entropy LOO selector reduces success at 25\% retention from 94.7\% to 74.0\% on \textit{can} and achieves 41.7\% on \textit{square}, below the mean success rates of all three independently sampled random subsets (59.8--62.5\%). On the same 3 \textit{square} Diffusion Policy training seeds, length-based selection at 75\% retention improves success over full-data training from 76.7\% to 86.7\% under the original protocol, but lowers it from 80.5\% to 79.5\% after checkpoint reporting, rollout count, and evaluation seed change jointly. No evaluated curated condition significantly outperforms full-data training after Holm correction, although confidence intervals still permit useful gains. Code is available at https://github.com/jiuyixu25/CuraEval.

cs.RO↗

arXiv2026

Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models

Post-training quantization (PTQ) reduces the memory footprint of vision-language-action (VLA) models, but lowering bit widths while maintaining task performance remains challenging. Existing work has used sensitivity estimates from calibration data to assign bit widths to different model components. However, using task success directly to guide mixed-precision allocation is underexplored because closed-loop evaluations are costly and the effect of quantizing one component depends on the precision of other components. To this end, we propose \textbf{QbD-VLA}, a task-guided mixed-precision quantization method that uses task success from short closed-loop evaluations to assign weight and activation bit widths while accounting for interactions between model components. Experiments covering four VLA models and all four LIBERO suites show strong task performance at average precisions of approximately 4 bits for weights and fewer than 6 bits for activations. On SIMPLER, the gain over uniform quantization is small. On a Franka Research 3 robot arm, simulation-selected allocations show no detected success-rate loss on X-VLA but fail on $π_{0.5}$. These findings support using task success to guide mixed-precision VLA quantization, while highlighting the need for real-world evaluation before deployment. Code is available at \href{https://github.com/jiuyixu25/QbD-VLA}{\texttt{github.com/jiuyixu25/QbD-VLA}}.

cs.RO↗

arXiv2026

PRISM: PRior-guided Imagination Sampling in world Models

Latent world models learn representations that enable them to predict how actions change the environment - a capability we call physical intuition. We find that these same representations also support action intuition: a lightweight head can learn a goal-conditioned action prior directly from the frozen encoder's features. We introduce PRISM to investigate how action intuition can be extracted from frozen world-model representations and used to guide goal-conditioned planning. The prior's mean and predicted uncertainty guide the search for useful actions, while the world model evaluates their consequences against the goal. Experiments on four simulated control tasks and two real-robot platforms show that a lightweight action head improves planning performance, and that the same fusion interface accepts a diffusion prior over the same frozen features without modification. These results demonstrate the potential of reusing world-model representations to both predict action consequences and guide action selection.

cs.RO↗

arXiv2026

World Models Dream of Success: Diagnosing and Repairing Failure Insensitivity in Robot World Models

Robot world models support policy evaluation, planning, and synthetic data generation, but these applications require predictions that distinguish successful actions from failures. Across four released checkpoints from two architecture families, we observe weak sensitivity to action changes and success-like predictions on verified failures. Although recent work incorporates failures into model training, which data can repair released checkpoints without changing their architecture or training objective still remains underexplored. To this end, we introduce CureWM, which constructs alternative actions from successful demonstrations across a severity grid, verifies their outcomes through execution in simulation or on hardware, and fine-tunes released models on the resulting failures and surviving successes alongside nominal demonstrations. This construction provides controlled action contrasts from shared starting contexts. On 484 held-out LIBERO failure counterfactuals, optimism falls from 80\% after fine-tuning on the official data to 30--43\% across four independently fine-tuned CureWM models (38\% mean). In two separate evaluations on a physical robot arm, failure predictions scored as success-like by a latent-distance diagnostic decrease from 90\% after fine-tuning on successful demonstrations alone to 33\% with CureWM. With failure counts per task, successful replay data, and training budget matched, counterfactual failures yield a success--failure value gap of 0.124, compared with 0.014 for freshly collected on-policy failures. These findings support execution-verified counterfactual replay for post-hoc repair and show why reduced optimism must be evaluated alongside success--failure discrimination. Code is available at https://github.com/jiuyixu25/CureWM.

cs.RO↗

arXiv2026

Nudge Before You Push: Physics-Aware Navigation via Tactile Probing

Visually identical containers can conceal loads that require different handling decisions. We present TANav, which uses a brief nudge to measure push resistance for navigation under a site-defined handling boundary. TacPhys reads the force sequence, with optional RGB-D and kinematics, into a mass estimate for push authorization. A repeated-patrol planner weighs probe and route costs, requests a second contact when useful, and reuses observations across visits. In simulation, TacPhys approaches a resistance-only Bayes reference and reduces missed pushes from 28.7% to 5.5% relative to peak-force thresholding at comparable low-risk operating points. In repeated-patrol simulation, TANav recovers 90% of the oracle's path saving, more than halves human interventions relative to always-detour, and reduces boundary violations from 4.3% to 2.9% relative to RGB-D-only probing. On a quadruped manipulator with a Hall-array fingertip, offline zero-shot MAE is 0.28-1.07 kg on containers up to 2.82 kg. Force-rise calibration at 3 kg gives 93.5% pooled offline accuracy (86.4% on non-cube episodes); a separate raw-peak rule gives 15 of 20 correct online decisions on unseen boxes.

cs.RO↗

arXiv2026

LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement

Color enhancement of 4K images must meet a quality target under a tight compute budget. Three-dimensional lookup tables (3D LUTs) dominate real-time enhancement because they decide at low resolution and apply a per-pixel lookup at full resolution. A single global LUT, however, is spatially invariant, so an underexposed shadow and a well-exposed region that share a pixel value receive identical corrections. Spatially heterogeneous demands cannot be expressed by such a mapping. We propose LoopLUT, a region-cascaded 3D LUT with progressive refinement. A global LUT performs the overall correction, followed by K-1 loop iterations. In each iteration a gating head predicts at low resolution the region that still needs correction, then builds a residual LUT from the color statistics of that region alone. The cascaded gates form a partition of unity, so the output is a per-pixel convex combination of the K lookup results. Fusion is therefore performed by the gates themselves, with no separate fusion module and no interpolation error accumulating across rounds. The decision stage runs at a fixed 256x256 resolution, independent of output resolution, so a 4K image costs only K pure lookups. Extensive experiments across four benchmarks show that LoopLUT improves PSNR by up to 2.81 dB over the strongest prior method, while keeping real-time throughput at 4K. The same decomposition also generalizes well to underwater enhancement datasets.

cs.CV↗

arXiv2026

SWE-Prime: Fewer Trajectories, Better Performance

To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning (SFT) on successful trajectories. However, task success does not guarantee high-quality supervision: successful trajectories may still contain ineffective, redundant, or risky steps. Directly using such trajectories for SFT can introduce noisy supervision and encourage models to imitate undesirable problem-solving behaviors. Therefore, we propose SWE-Prime, a multi-granularity, two-stage SFT data selection method that progressively filters training data at the trajectory and segment levels. Specifically, the first stage performs trajectory-level screening based on process quality, result quality, and data representativeness, selecting a high-quality and representative subset of successful trajectories. The second stage performs segment-level selection by grouping consecutive steps into semantic segments and assessing each segment based on its contribution to the final solution, learnability, and potential risks. During SFT, all segments remain in the sequence to preserve context, while only selected segments contribute to the loss computation. Experiments on SWE-Bench Pro and SWE-Bench Verified show that training on the 10% trajectory subset selected by SWE-Prime outperforms training on the full resolved dataset, yielding relative performance gains of up to 12.2% and 24.2%, respectively.

cs.SE↗

arXiv2026

Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors

Estimating interpretable conditional-dependence structures from multimodal visual-linguistic features remains largely unexplored. We propose CM-GLasso (Cross-Modal Graphical Lasso), a framework that bridges vision-language representation learning and sparse Gaussian Graphical Models. CM-GLasso introduces three key components: (i) a text visualization strategy that renders class-attribute descriptions as images and processes them through the same SigLIP-2 vision encoder as natural images, yielding prototype-indexed patch-level attention footprints in a shared feature coordinate system; (ii) a cross-attention distillation mechanism that condenses high-dimensional patches into a small set of semantic graph nodes, whose attention-footprint similarities yield cross-modal structural priors for non-uniform L1 penalization; (iii) a joint ADMM formulation that estimates shared and class-specific precision components within a single convex objective, avoiding the need to first estimate and then decompose separate class-wise graphs. The learned sparse graph topologies directly support a parameter-free, precision-based classification rule and a lightweight topology-aware segmentation head. Extensive experiments on eight benchmarks demonstrate that CM-GLasso achieves competitive or superior performance compared with strong feature-based and task-specific baselines. Under the matched controlled protocol, it attains the highest average classification accuracy (91.97%) and the highest segmentation mIoU among the controlled baselines on VOC (74.75%) and ADE20K (64.01%), while also yielding explicit sparse conditional-dependence graphs with common-specific decomposition.

cs.CV↗

arXiv2026

Heterogeneous 2D/1D Signal Representation Fusion for Underwater Acoustic Modulation Recognition Under Distribution Shift

Modulation recognition systems rely on heterogeneous signal representations. 2D signal-image modalities such as time-frequency and cyclostationary maps capture structural patterns, while 1D statistical descriptors such as higher-order power spectra encode complementary cues. Under distribution shift, these modalities degrade unevenly, making robust fusion a central challenge for practical deployment. Progress is further limited by the lack of a unified evaluation protocol that systematically separates different shift types. This paper addresses both challenges through a joint benchmark-and-model study in underwater acoustic modulation recognition. UAMR-ShiftBench is the first benchmark to jointly cover in-distribution, low-SNR, unseen-environment, unseen-communication-parameter, and measured sea-trial evaluation under a single matched protocol, with two independent real-world subsets collected during two sea-trial campaigns conducted in March and November in the South China Sea. SCP-TriCA fuses STFT, cyclostationary, and P2/P4 (second- and fourth-order power spectra) modalities hierarchically: the two 2D modalities are first aligned through bidirectional cross-attention, and the 1D statistical modality is then incorporated through a sample-adaptive selective gate. On UAMR-ShiftBench, SCP-TriCA achieves 95.33% in-distribution accuracy and 74.59% simulated OOD average, outperforming the strongest baseline by 5.12 percentage points, and reaches 91.14% and 94.86% on the two sea-trial subsets, exceeding the best baseline by 15.71 and 23.00 percentage points respectively. Ablation results confirm that the gains stem from modality complementarity and the hierarchical fusion design. Code and models are available at https://github.com/ronglaiqian/UAMR-ShiftBench.

eess.AS↗

arXiv2026

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw video data often fail to capture meaningful geometric-aware structure in their learned representations. To bridge the gap between video diffusion models and the underlying 3D nature of the physical world, we propose Geometry Forcing, a simple yet effective method that encourages video diffusion models to internalize 3D representations. Our key insight is to guide the model's intermediate representations toward geometry-aware structure by aligning them with features from a geometric foundation model. To this end, we introduce two complementary alignment objectives: Angular Alignment, which enforces directional consistency via cosine similarity, and Scale Alignment, which preserves scale-related information by regressing geometric features from normalized diffusion representations. We evaluate Geometry Forcing on both camera-view conditioned and action-conditioned video generation tasks. Experimental results demonstrate that our method substantially improves visual quality and 3D consistency over the baseline methods. Project page: https://GeometryForcing.github.io.

cs.CV↗

arXiv2026

Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs

Training effective software engineering agents requires large volumes of task-specific trajectories, incurring substantial data construction costs. Inspired by the "Less-Is-More" hypothesis in mathematical reasoning, we investigate its extension to agentic scenarios and propose an end-to-end training framework that achieves superior agentic capabilities with fewer but higher-quality training trajectories. This is achieved via STITCH (Sliding-memory Trajectory Inference and Task Chunking Heuristic), a coarse-to-fine mechanism that filters low-value noise and retains decision-critical tokens to maximize training signal quality. We conduct experiments across multiple agent frameworks (e.g., mini-SWE-agent, MSWE-agent), model scales (30B to 355B), and multilingual settings (Python, Java, and ArkTS). On SWE-bench Verified, models trained with STITCH achieve up to 63.16% relative improvement over base models. On Multi-SWE-bench (Java), MiniMax-M2.5-STITCH achieves 43.75% with our CodeArts Agent scaffold (+16.67%). On HarmonyOS (ArkTS), GLM-4.7-STITCH improves the compilation pass rate to 61.31% (+43.34%) with less than 1K training trajectories. Our results confirm that the "Less-Is-More" paradigm generalizes effectively to complex agentic tasks across diverse languages and model scales.

cs.SE↗

arXiv2026

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can improve reprojection-based consistency but struggle to depict moving objects, while implicit memory often produces inaccurate camera motion even with correct poses. We propose Mosaic Memory (MosaicMem), a hybrid spatial memory that lifts patches into 3D for reliable localization and targeted retrieval, while exploiting the model's native conditioning to preserve prompt-following generation. MosaicMem composes spatially aligned patches in the queried view via a patch-and-compose interface, preserving what should persist while allowing the model to inpaint what should evolve. With PRoPE camera conditioning and two new memory alignment methods, experiments show improved pose adherence compared to implicit memory and stronger dynamic modeling than explicit baselines. MosaicMem further enables minute-level navigation, memory-based scene editing, and autoregressive rollout.

cs.CV↗

arXiv2026

UniPrototype: Humn-Robot Skill Learning with Uniform Prototypes

Data scarcity remains a fundamental challenge in robot learning. While human demonstrations benefit from abundant motion capture data and vast internet resources, robotic manipulation suffers from limited training examples. To bridge this gap between human and robot manipulation capabilities, we propose UniPrototype, a novel framework that enables effective knowledge transfer from human to robot domains via shared motion primitives. ur approach makes three key contributions: (1) We introduce a compositional prototype discovery mechanism with soft assignments, enabling multiple primitives to co-activate and thus capture blended and hierarchical skills; (2) We propose an adaptive prototype selection strategy that automatically adjusts the number of prototypes to match task complexity, ensuring scalable and efficient representation; (3) We demonstrate the effectiveness of our method through extensive experiments in both simulation environments and real-world robotic systems. Our results show that UniPrototype successfully transfers human manipulation knowledge to robots, significantly improving learning efficiency and task performance compared to existing approaches.The code and dataset will be released upon acceptance at an anonymous repository.

cs.RO↗

arXiv2026

Spatially anchored Tactile Awareness for Robust Dexterous Manipulation

Dexterous manipulation requires precise geometric reasoning, yet existing visuo-tactile learning methods struggle with sub-millimeter precision tasks that are routine for traditional model-based approaches. We identify a key limitation: while tactile sensors provide rich contact information, current learning frameworks fail to effectively leverage both the perceptual richness of tactile signals and their spatial relationship with hand kinematics. We believe an ideal tactile representation should explicitly ground contact measurements in a stable reference frame while preserving detailed sensory information, enabling policies to not only detect contact occurrence but also precisely infer object geometry in the hand's coordinate system. We introduce SaTA (Spatially-anchored Tactile Awareness for dexterous manipulation), an end-to-end policy framework that explicitly anchors tactile features to the hand's kinematic frame through forward kinematics, enabling accurate geometric reasoning without requiring object models or explicit pose estimation. Our key insight is that spatially grounded tactile representations allow policies to not only detect contact occurrence but also precisely infer object geometry in the hand's coordinate system. We validate SaTA on challenging dexterous manipulation tasks, including bimanual USB-C mating in free space, a task demanding sub-millimeter alignment precision, as well as light bulb installation requiring precise thread engagement and rotational control, and card sliding that demands delicate force modulation and angular precision. These tasks represent significant challenges for learning-based methods due to their stringent precision requirements. Across multiple benchmarks, SaTA significantly outperforms strong visuo-tactile baselines, improving success rates by up to 30 percentage while reducing task completion times by 27 percentage.

cs.RO↗

arXiv2026

CausalGDP: Causality-Guided Diffusion Policies for Reinforcement Learning

Reinforcement learning (RL) has achieved remarkable success in a wide range of sequential decision-making problems. Recent diffusion-based policies further improve RL by modeling complex, high-dimensional action distributions. However, existing diffusion policies primarily rely on statistical associations and fail to explicitly account for causal relationships among states, actions, and rewards, limiting their ability to identify which action components truly cause high returns. In this paper, we propose Causality-guided Diffusion Policy (CausalGDP), a unified framework that integrates causal reasoning into diffusion-based RL. CausalGDP first learns a base diffusion policy and an initial causal dynamical model from offline data, capturing causal dependencies among states, actions, and rewards. During real-time interaction, the causal information is continuously updated and incorporated as a guidance signal to steer the diffusion process toward actions that causally influence future states and rewards. By explicitly considering causality beyond association, CausalGDP focuses policy optimization on action components that genuinely drive performance improvements. Experimental results demonstrate that CausalGDP consistently achieves competitive or superior performance over state-of-the-art diffusion-based and offline RL methods, especially in complex, high-dimensional control tasks.

cs.LG↗

arXiv2025

Cross-platform Product Matching Based on Entity Alignment of Knowledge Graph with RAEA model

Product matching aims to identify identical or similar products sold on different platforms. By building knowledge graphs (KGs), the product matching problem can be converted to the Entity Alignment (EA) task, which aims to discover the equivalent entities from diverse KGs. The existing EA methods inadequately utilize both attribute triples and relation triples simultaneously, especially the interactions between them. This paper introduces a two-stage pipeline consisting of rough filter and fine filter to match products from eBay and Amazon. For fine filtering, a new framework for Entity Alignment, Relation-aware and Attribute-aware Graph Attention Networks for Entity Alignment (RAEA), is employed. RAEA focuses on the interactions between attribute triples and relation triples, where the entity representation aggregates the alignment signals from attributes and relations with Attribute-aware Entity Encoder and Relation-aware Graph Attention Networks. The experimental results indicate that the RAEA model achieves significant improvements over 12 baselines on EA task in the cross-lingual dataset DBP15K (6.59% on average Hits@1) and delivers competitive results in the monolingual dataset DWY100K. The source code for experiments on DBP15K and DWY100K is available at github (https://github.com/Mockingjay-liu/RAEA-model-for-Entity-Alignment).

cs.AI↗

arXiv2025

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their ability to explore and generalize beyond training distributions. To this end, we introduce Edit-R1, a novel post-training framework for instruction-based image editing based on policy optimization. Specifically, we utilize Diffusion Negative-aware Finetuning (DiffusionNFT), a likelihood-free policy optimization method consistent with the flow matching forward process, thereby enabling the use of higher-order samplers and more efficient training. Another key challenge here is the absence of a universal reward model, resulting from the diverse nature of editing instructions and tasks. To bridge this gap, we employ a Multimodal Large Language Model (MLLM) as a unified, training-free reward model, leveraging its output logits to provide fine-grained feedback. Furthermore, we carefully design a low-variance group filtering mechanism to reduce MLLM scoring noise and stabilize optimization. \texttt{UniWorld-V2}, trained with this framework, achieves \textbf{state-of-the-art} results on the ImgEdit and GEdit-Bench benchmarks, scoring 4.49 and 7.83, respectively. Crucially, our framework is model-agnostic, delivering substantial performance gains when applied to diverse base models like Qwen-Image-Edit and FLUX-Kontext, demonstrating its wide applicability. Code and models are publicly available to support further research.

cs.CV↗