arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 73 records · Page 4Linked to original sources

arXiv2026

RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction

Retrosynthesis is a cornerstone of drug discovery and organic synthesis. While data-driven deep learning models have shown remarkable progress, they autonomously learn reaction patterns from extensive datasets with limited integration of established chemical knowledge as priors. To address this limitation, we introduce RetroMPA, a molecular property-aware, post-hoc enhancement module that injects chemical knowledge into the retrosynthesis pipeline. Rather than functioning as an independent SMILES sequence generator, RetroMPA is a broadly applicable, model-agnostic chemical filter designed to recalibrate and optimize the predictive pathways of existing algorithms. This plug-and-play framework integrates seamlessly with a range of data-driven retrosynthesis methods, enhancing outputs without modifying model architecture or requiring resource-intensive retraining. By leveraging a property-aware latent embedding space, RetroMPA consistently improves top-1 accuracy across eight representative retrosynthesis models by an average of 5.50% on USPTO-50K. Furthermore, we validate its scalability on the large-scale USPTO-Full dataset, achieving an average improvement of about 2.03% across both template-based and template-free architectures. Wet-lab experiments provide preliminary support for the practical utility of the framework. These syntheses confirmed viable, previously unreported substrate combinations for classic reaction paradigms---specifically, Suzuki-Miyaura coupling, Bucherer reaction, and Friedel-Crafts acylation---suggesting that RetroMPA can operate beyond mere data fitting. The code is open-sourced at https://github.com/MengzhouLu/RetroMPA.

cs.LG↗

arXiv2026

BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning

Fragment-level representations provide a natural way to capture recurring molecular substructures and reuse their learned representations across molecules. However, a shared fragment identity alone may not fully describe how a fragment is instantiated in a particular molecule, since the same fragment can exhibit different chemical behavior depending on its surrounding atomic environment. Effective fragment-based molecular learning therefore requires representations that are both reusable across molecules and sensitive to local atomic context. We introduce BiScale-GTR, a self-supervised molecular representation framework built around context-grounded shared fragment tokens. BiScale-GTR constructs a reusable graph Byte Pair Encoding (graph-BPE) vocabulary using Weisfeiler-Lehman (WL)-based fragment identity, chemical validity filtering, and recursive out-of-vocabulary (OOV) decomposition. Each shared fragment token is then grounded with atom-level GNN representations through atom-to-fragment pooling and gated fusion, allowing the same fragment identity to acquire context-dependent representations in different molecular environments. A structure-aware fragment Transformer performs global reasoning over these atom-grounded tokens, capturing reusable substructure identity, local chemical context, and long-range molecular dependencies. Experiments on MoleculeNet, PharmaBench, and the Long Range Graph Benchmark demonstrate strong performance across classification and regression tasks. Attribution analysis further shows that BiScale-GTR highlights chemically meaningful recurring motifs, providing interpretable links between molecular structure and predicted properties.

cs.LG↗

arXiv2026

JWST Spectroscopy of Type Ia Supernova 2025rbs from Maximum Light to the Nebular Phase

We present JWST observations of the Type Ia supernova (SN Ia) 2025rbs ($D=$14.5 Mpc) at +1, +23, and +84 days after B-band maximum, spanning peak light through a wavelength-dependent transition toward the nebular phase. Combined with ground-based optical and near-infrared (NIR) data, our panchromatic spectra (0.4-14 $μ$m) include the first maximum-light mid-infrared (MIR) spectrum and the earliest MIR spectroscopic sequence of an SN Ia to date. At peak light, the MIR spectrum exhibits a continuum with permitted and forbidden features, including Si II, Ni II, and early-emerging [Ni III-IV] and [Ar II-III]. By +23 days the MIR is dominated by forbidden lines with a weak continuum, and by +84 days it is fully nebular, whereas the optical/NIR spectra remain transitional. The nebular spectrum reveals strongly stratified ejecta, with stable Ni concentrated at the lowest velocities, radioactive Co at intermediate velocities but absent within ~2000 km s$^{-1}$, and Ar occupying an outer shell. We detect small-scale substructure in [Ca IV] 3.21 $μ$m with fractional amplitudes of a few percent and a characteristic velocity scale of ~800 km s$^{-1}$, which may reflect compositional structure, ionization variations, or both. Radiative-transfer calculations substantially underpredict these MIR Mg II features despite approximately reproducing the NIR Mg II 1.0927 $μ$m line, suggesting that the relative strengths of these transitions are sensitive to the treatment of Mg ionization and excitation. These observations demonstrate that MIR spectroscopy beginning near maximum light simultaneously probes the emerging inner ejecta and rapidly fading outer burning products, providing new constraints for explosion and radiative-transfer models.

astro-ph.HE↗

arXiv2026

Beyond Pixels: From Video Priors to 4D Worlds

4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video generator to predict geometry directly. The former suffers from distribution mismatch and error propagation, whereas the latter ties 4D prediction to a specific generator and may require retraining when the generator or conditioning regime changes. We ask whether the final denoised latents of video models that share a variational autoencoder (VAE) can instead provide a reusable interface to explicit 4D prediction. Building on this insight, we introduce direct latent-to-4D generation and instantiate it as Latent-to-4D, which bypasses RGB by aligning a video latent with the token grid of a pretrained 4D decoder and refining it through frame-wise and global spatiotemporal attention. Trained on roughly 1K existing reconstruction clips, a single checkpoint transfers unchanged across multiple video diffusion transformers within the same VAE family. On Text4D-200 and I4D-200, Latent-to-4D surpasses matched same-latent Wan+4RC cascades in projection-based DINO-F1 by 2.88--3.45 and 5.81 points, respectively, while also being preferred by human raters for geometry, temporal stability, and overall quality.

cs.CV↗

arXiv2026

RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States

Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-indexed utilities grow with the interaction history, thereby dispersing limited feedback over an ever-expanding state space. Second, because trajectory-level rewards are jointly assigned to co-retrieved memories, irrelevant experiences may receive misleading utility updates and consequently enter the memory-reward trap. To address these challenges, we introduce Reduced-Order Memory Reinforcement Learning (RoMeRL), which represents the growing trajectory-indexed utility space using a fixed-dimensional per-task memory state factorized by outcome polarity and memory dynamics. RoMeRL incorporates new experiences through a fixed set of semantic coordinates whose contents are updated or replaced over time, thereby concentrating feedback over a bounded utility support. Theoretically, we show that this reduced-order parameterization increases the average feedback received by each utility coordinate and characterize the steady-state occupancy of erroneous coordinates under a generic coordinate-transition model. Empirically, across ALFWorld and LifelongAgentBench, RoMeRL improves task performance, reduces the Cold-Q ratio by 80.0%, increases feedback density by approximately 6.0 times, reduces the maintained memory size by 84.4%, and cuts LLM calls by 21.1%. These results show that reduced-order utility states support efficient self-evolving agent memory while limiting persistent reward contamination. Code is available at: https://github.com/YOUNG-fnxm/RoMeRL

cs.LG↗

arXiv2026

Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks

Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few samples convey the trigger--target association, making poison-sample selection critical. Existing methods typically rank candidates using per-sample scores, which can select redundant samples from similar semantic regions, and many require task-specific surrogate training. We propose Distributional Feature Coverage Sample Selection (DFCS), a training-free, trigger-agnostic method that clusters fixed pretrained features into one region per poisoning slot and selects the centroid-nearest sample from each region. A local first-order analysis relates this allocation to feature-coverage and representative-mass terms. Across BadNets and Blended attacks on CIFAR-10, Tiny-ImageNet, and Imagenette, DFCS achieves the highest mean attack success rate among seven selectors in all six dataset--attack settings, averaging $96.30\%$ and exceeding the strongest comparator in each setting by 4.60 percentage points on average while preserving clean accuracy. These results support distributional feature coverage as an effective selection principle for low-budget dirty-label backdoor attacks.

cs.CR↗

arXiv2026

PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing

Achieving physically accurate object manipulation in image editing is essential for its potential applications in interactive world models. However, existing visual generative models often fail at precise spatial manipulation, resulting in incorrect scaling and positioning of objects. This limitation primarily stems from the lack of explicit mechanisms to incorporate 3D geometry and perspective projection. To achieve accurate manipulation, we develop PhyEdit, an image editing framework that leverages explicit geometric simulation as contextual 3D-aware visual guidance. By combining this plug-and-play 3D prior with joint 2D--3D supervision, our method effectively improves physical accuracy and manipulation consistency. To support this method and evaluate performance, we present a real-world dataset, RealManip-40K, for 3D-aware object manipulation featuring paired images and depth annotations. We also propose ManipEval, a benchmark with multi-dimensional metrics to evaluate 3D spatial control and geometric consistency. Extensive experiments show that our approach outperforms existing methods, including strong closed-source models, in both 3D geometric accuracy and manipulation consistency.

cs.CV↗

arXiv2026

From Points to Edges: Edge-Conditioned Spectral Operators for Physics-Sensitive PDE Learning

Neural operators have become a central tool for solving partial differential equations (PDEs), with spectral operators offering efficient global mixing across spatial locations. However, many PDEs contain physics-sensitive local structures that are critical to the underlying physical behavior. For example, in Darcy flow, local material interfaces are often reflected by sharp changes in the permeability field and can strongly influence the solution. Existing spectral operators primarily adapt modal mixing based on center-point representations, making them insufficiently responsive to such localized structural variations. We propose the Edge-Conditioned Spectral Operator (ESO), a novel spectral operator framework that modulates global spectral mixing using local edge-wise variations. By incorporating the Pairwise-Variation Modal Mixer (PVMM) to inject local edge information into spectral mode selection, ESO preserves the global approximation capability of spectral neural operators while enabling the learned kernel to adapt to physics-sensitive local structures. Furthermore, we introduce a task-adaptive Physics-Aware Reweighting (PAR) that emphasizes physically important regions, identified by taskspecific physical quantities. Across nine PDE benchmarks, ESO consistently achieves state-of-the-art performance. Visual and region-wise analyses further demonstrate that ESO reduces solution errors near coefficient jumps, high-gradient flow structures, and other physically sensitive regions. The code is available at https://github.com/Tanpig-X/ESO.

cs.AI↗

arXiv2026

Pinning Down the Geometry of the Type Ic Broad-Line Supernova 2026gzf

Type Ic broad-line supernovae (SNe Ic-BL) are often associated with energetic explosions that display a prompt outburst of high-energy emission. Since their progenitor lost the H and He envelopes before the explosion exposing the C/O core, their explosion dynamics and geometry can be seen in an unobscured and undistorted way. We present imaging polarimetry and spectropolarimetry of the Type Ic-BL SN 2026gzf obtained 4.6 and 16.5 days after the X-ray shock breakout, which was recorded by the Einstein Probe satellite as EP260321a, showing it to be one of the softest and intrinsically dimmest extragalactic fast X-ray transients. The persistent low continuum polarization indicates that the outer layer of SN 2026gzf is mostly spherical, suggesting the explosion did not significantly disrupt the progenitor envelope. At day 16.5, the calcium near-infrared triplet displays a peak polarization above 1.5%. The geometry of the associated line opacity is also compatible with an axisymmetric configuration. The spatial distribution of such oxygen-burning ashes thus indicates the presence of a symmetry axis of the excitation structure within the nearly spherical ejecta. The Ca II triplet profile is dominated by a primary component spanning ~25,000--40,000 km/s, alongside a distinct secondary component extending above 28,000 km/s whose polarization implies a non-axisymmetric, complex excitation geometry toward the outer ejecta By implementing a three-dimensional Monte-Carlo calculation, we infer that a viewing angle of ~40 degree from the symmetry axis of the excitation structure could plausibly reproduce the observed spectral and polarization profiles of the Ca II triplet.

astro-ph.HE↗

arXiv2026

Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation

On-policy distillation (OPD) provides teacher supervision on states visited by the student, reducing the distribution gap between training and inference. However, in multi-turn agentic tasks, student deviations may accumulate over time, gradually moving the trajectory away from states where teacher guidance remains effective. Our quantitative analysis further shows that high-disagreement states offer promising opportunities for teacher guidance, but determining whether such guidance is beneficial requires examining its effect on subsequent student trajectories. We propose FutureBridge-OPD (FTB), which executes a short teacher bridge at a high disagreement state and uses the resulting student continuation to assess whether the bridge increases the density of positive distillation signals relative to the teacher. On ALFWorld, WebShop, and ScienceWorld, under the main Qwen3-32B teacher to Qwen3-1.7B student setting, FTB outperforms vanilla OPD and TCOD by an average of 16.6 and 7.6 points, respectively, and remains effective across student scales and teacher settings. Our code is publicly available at https://github.com/ChenChiShui/FutureBridge-OPD.

cs.CL↗

arXiv2026

Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation

Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated. On-Policy Self-Distillation (OPSD) addresses this by re-scoring generated tokens under a privileged replay view to obtain dense, token-level supervision. However, we identify a confounding issue: the resulting support may reflect both the privileged information contained in the replay view and score shifts induced by the replay scaffold, making it difficult to attribute the support specifically to that information. This issue is especially pronounced when future environment observations serve as privileged information, since replaying them requires reconstructing an extended scaffold that itself perturbs token scores. To resolve this confounding, we propose Observation-Calibrated Self-Distillation (OCSD), which contrasts two structurally matched replay views, Full and Observation-Ablated, differing only in whether the actual future observation is present, to derive an observation residual that discounts score changes shared by the replay scaffold. OCSD then applies this residual to modulate token-level GRPO updates at high-uncertainty steps, while preserving the trajectory-level update direction. Experiments on ALFWorld, WebShop, and Search-QA across three Qwen3 model scales show that OCSD consistently outperforms strong baselines. Diagnostic analyses further confirm that the calibrated residual aligns better with local environment feedback. Our code is publicly available at https://github.com/yiy1x/OCSD.

cs.LG↗

arXiv2026

Data-DPO: Direct Preference Optimization for Target Model Data Selection in LLM Post-Training

Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance. However, existing methods usually treat data value as a relatively static property, and pay limited attention to the compatibility between data and the capability distribution of the target model. To address this issue, we propose Data-DPO, a target model-oriented SFT data selection method. Data-DPO observes the local training feedback of the target model on different samples through one-step probing, transforms activation differences among samples into pairwise data preferences, and trains a lightweight reward model to learn target-model-aware data preferences. In the final selection stage, Data-DPO further combines target model preference, external quality scores, and marginal diversity to construct a more stable and effective training subset. Experimental results on Vision-Flan and LLaVA-CoT show that Data-DPO consistently outperforms existing data selection baselines under multiple data budgets and stably surpasses full data training performance.

cs.LG↗

arXiv2026

Hierarchical Data Selection via Manifold Coverage and Sparse Feature Coverage in LLM Post-training

As supervised fine-tuning data continues to scale, selecting high-value subsets from large candidate pools is crucial for reducing training cost and improving model performance. Existing methods often measure diversity directly in the original embedding space, where geometric metrics entangle dominant semantic directions, fine-grained supervision differences, and local noise. We address this limitation by formulating data selection as a coarse-to-fine hierarchical coverage problem and propose MASS. MASS learns low-dimensional principal manifold coordinates with a dense autoencoder for coarse semantic grouping, and then performs quality-aware sparse feature coverage within each group using a TopK sparse autoencoder. Experiments on Vision Flan and LLaVA-CoT show that MASS consistently outperforms strong data selection baselines across multiple budgets, and in several settings matches or surpasses full data training with only a small subset of data.

cs.LG↗

arXiv2026

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion

Autoregressive video generators synthesize long videos by generating successive temporal segments, but their historical KV cache grows with video length. Existing bounded-cache methods reduce this cost with local windows, sink tokens, or compressed memory states, yet they usually assign fixed roles to different parts of the history. We propose FadeMem, a distance-aware KV memory consolidation mechanism that organizes historical KV blocks into a temporal hierarchy under a fixed cache budget. This design is motivated by frequency-dependent temporal decay: fine details decorrelate quickly, while coarse scene structure and identity remain useful over longer horizons. During generation, new history is inserted as fine-grained entries, while older adjacent entries are progressively merged under a power-law temporal allocation schedule, yielding a dense-near, sparse-far memory within one cache. Without architectural changes, FadeMem improves long-range consistency while largely preserving visual quality, and lightweight adaptation further enhances motion dynamics and visual fidelity. Using the same unified schedule under a fixed cache budget, FadeMem also remains effective over multi-minute and hour long video generation and reduces peak memory under a matched KV budget.

cs.CV↗

arXiv2026

Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL

Offline reinforcement learning (offline RL) can benefit from nearby out-of-distribution (OOD) actions, but estimation errors at these actions may be amplified by bootstrapping. Existing regularization and local-generalization methods control either the admissible OOD region or the influence of generalized targets, often through separate mechanisms. We propose Convex Hull Neighborhood Smooth Dual Generalization (CSDG), which expresses the Bellman backup as an in-sample value target plus a CHN-local correction. This formulation makes the generalized contribution explicit and separates it from the in-sample reference path. The correction is obtained by smoothing in-sample-oriented and OOD-oriented candidates sampled at different perturbation radii. A mixture coefficient lambda scales its contribution to each backup, while the recursive discount remains gamma. Under boundedness and fixed perturbation kernels, we derive an exact one-step correction identity, a time-varying iterate bound, and a fixed-point bound that depends only on the branch discrepancy at the fixed point. We further characterize the implicit policies induced by the idealized operators and give a conditional non-degradation criterion. The practical algorithm approximates these quantities using asymmetric bounded noise and expectile regression, without exact support classification or an additional pessimistic OOD penalty. Experiments on Gym-MuJoCo and AntMaze show strong aggregate performance and stable value estimation. Code is available at: https://github.com/YOUNG-fnxm/CSDG

cs.LG↗

arXiv2026

DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms

Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs). In this paper, we propose \textbf{DAG-FM}, a novel foundation model architecture that amortizes causal discovery. Unlike direct matrix prediction, DAG-FM decomposes the causal discovery process into two auto-regressive stages using two specialized Transformer-based sub-modules: a leaf-node predictor and a parent-node predictor. To effectively model complex row-column interactions, we adopt a robust tabular interaction block to output feature-wise representations. Crucially, to handle diverse and unknown Functional Causal Model (FCM) assumptions in real-world scenarios, we introduce Mixture-of-Leaf-Experts (MoLE), allowing the model to dynamically route and adapt to identifiable mechanism families. Through an iterative inference algorithm, DAG-FM seamlessly extracts causal orderings and constructs valid DAGs. Extensive experiments demonstrate that DAG-FM achieves state-of-the-art performance on both synthetic benchmarks and complex real-world datasets, significantly outperforming traditional classical algorithms and recent foundation models in both accuracy and scalability.

cs.LG↗

arXiv2026

Agentic Graph Token Reasoning

Graphs model relational data throughout science and industry, from citation networks to product co-purchase graphs. Because the nodes of many such graphs carry rich text, a growing line of work applies large language models (LLMs) to graph analysis. The most graph-native of these methods use graph tokens: a graph encoder compresses a graph view, such as a node, its k-hop neighbourhood, or a cluster, into a short block of continuous tokens that jointly encodes node attributes and topology and is read directly by the model. Existing methods, however, use graph tokens in a static single-shot manner: they encode one predefined graph view before the model has even seen the target and never revise it, leaving the model's step-by-step reasoning ability unused. We introduce agentic graph token reasoning, which recasts graph tokenization as part of the reasoning process itself. At each step, the model chooses which graph view to encode and at what granularity; a graph encoder is invoked on demand to materialise the corresponding graph tokens; and the resulting block is spliced into the running context. The model thus reasons step by step in the graph token space, and the tokens it reads are trajectory-dependent. We realise this with a three-stage training pipeline: (i) self-supervised tasks that teach the model to read heterogeneous graph tokens, (ii) a token-robust trajectory stage with a graph-token consistency regulariser, and (iii) preference optimisation that rewards trajectories in which the graph-token evidence and the node-text evidence agree. Across evaluations spanning seven graph domains, our models outperform a broad set of baselines by a large margin and transfer zero-shot to unseen domains without any per-target fine-tuning. More broadly, this work pushes LLM-based graph analysis from static graph-token encoders towards a graph-native agent paradigm.

cs.LG↗

arXiv2026

TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking

Existing 3D Gaussian Splatting (3DGS) editing methods primarily focus on appearance modification and often struggle to support flexible geometry editing while preserving structural integrity and scene-consistent appearance. To address this limitation, we present TRACE, a mesh-guided 3DGS editing framework that automatically aligns explicit 3D geometry with Gaussian scenes and decouples Geometric Anchoring from Appearance Harmonization. First, Multi-view 3D-Anchor Synthesis, trained on our MV-TRACE dataset for scene-coherent object addition and modification, generates geometrically aligned editing anchors, while Tangible Geometry Alignment (TGA) performs coarse-to-fine mesh-scene registration. Then, Contextual Video Masking (CVM) integrates projected 3D anchors into an autoregressive video diffusion pipeline, harmonizing their appearance with the surrounding scene while maintaining multi-view consistency. We evaluate TRACE on eight held-out scenes across six editing categories. TRACE completes each edit in approximately 10 minutes on a single NVIDIA RTX Pro 6000 GPU. Extensive experiments demonstrate consistent improvements over existing methods in editing versatility, structural integrity, semantic alignment, multi-view consistency, and visual quality.

cs.CV↗