R
Published on

CVPR 2026 — Other / Unclassified

Other / Unclassified

333 papers

1. Beyond Euclidean Gossip: KL-Barycentric Consensus on Heterogeneous and Imbalanced Images

2. What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely F1

3. LongStream: Long-Sequence Streaming Autoregressive Visual Geometry

4. POUR: A Provably Optimal Method for Unlearning Representation via Neural Collapse

5. A Training-Free Style-Personalization via SVD-Based Feature Decomposition

6. Unlocking Token Rewards via Training-Free Reward Attribution

7. Learning What Helps: Task-Aligned Context Selection for Vision Tasks

8. Event Structural Valley: A Unified Theoretical and Practical Framework for Event Camera Autofocus

9. Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

10. FoV-Net: Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting

11. Global Information Thresholding for Sufficient and Necessary Circuits

12. Complet4R: Geometric Complete 4D Reconstruction

13. Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization

14. Affine Perspective-Three-Point Problem

15. Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks

16. Long-Tail Internet Photo Reconstruction

17. X-band Radar Non-Line-of-Sight Imaging

18. OMG-Avatar: One-shot Multi-LOD Gaussian Head Avatar

19. Envisioning the Future, One Step at a Time

20. ID-Sim: An Identity-Focused Similarity Metric

21. HumanBA: Human-Aware Bundle Adjustment via Global Human-Camera Decoupling

22. Lens Component Deletion based on Differentiable Ray Tracing

23. Variational Graph-based Normal Integration

24. LNEM: Lunar Neural Elevation Model

25. OrionEdit: Bridging Reference and Source Images for Generalized Cross-Image Editing

26. Event Stream Filtering via Probability Flux Estimation

27. Event-based Visual Deformation Measurement

28. Lipschitz Optimization for Formal Verification of Homographies

29. Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models

30. MatE: Material Extraction from Single-Image via Geometric Prior

31. UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass

32. Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification

33. From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal

34. AvatarPointillist: AutoRegressive 4D Gaussian Avatarization

35. CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics

36. Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding

37. AudioAvatar: Personalized Audio-driven Whole-body Talking Avatars

38. Monet: Reasoning in Latent Visual Space Beyond Image and Language

39. GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport

40. When to Think and When to Look: Uncertainty-Guided Lookback

41. VGA: Empowering Aerial-Ground Localization by Visual Geometry Alignment

42. PositionIC: Unified Position and Identity Consistency for Image Customization

43. PrivateEyes: Gaze-Preserving Anonymization for Data Sharing

44. GUI-SAGE: Enhancing GUI Automation with Self-Explanatory Learning

45. A3: Towards Advertising Aesthetic Assessment

46. Hier-COS: Making Deep Features Hierarchy-aware via Composition of Orthogonal Subspaces

47. MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments

48. Revisiting Optimal Coding for I-ToF under Practical Sensor Constraints

49. Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors

50. Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling

51. Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy

52. Global Underwater Geolocation from Time-Lapse Polarization Imagery

53. CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion

54. ARC Is a Vision Problem!

55. Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis

56. PRISM: Learning a Shared Primitive Space for Transferable Skeleton Action Representation

57. Beyond Single-View Sufficiency: CVBench for Cross-View Human Understanding

58. Rethinking Concept Bottleneck Models: From Pitfalls to Solutions

59. Spectrum from Defocus: Fast Spectral Imaging with Chromatic Focal Stack

60. Your Dissimilarities Define You: Complementary Learning Exploiting Class Diversities

61. Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks

62. Bridging Domains through Subspace-Aware Model Merging

63. Dynamic Black-hole Emission Tomography with Physics-informed Neural Fields

64. Vision-Speech Models: Teaching Speech Models to Converse about Images

65. SplitFlux: Learning to Decouple Content and Style from a Single Image

66. A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction

67. Bridging Domain Expertise and Generalization for Performance Estimation

68. Pano360: Perspective to Panoramic Vision with Geometric Consistency

69. CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization

70. Learning Personalized Photographic Style from Pairwise User Preferences

71. Omni-MMSI: Toward Identity-attributed Social Interaction Understanding

72. Stable Spike: Dual Consistency Optimization via Bitwise AND Operations for Spiking Neural Networks

73. Rethinking Cross-Modal Anchor Alignment for Mitigating Error Accumulation

74. X-WIN: Building Chest Radiograph World Model via Predictive Sensing

75. D-Prism: Differentiable Primitives for Structured Dynamic Modeling

76. Neural Collapse in Test-Time Adaptation

77. Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models

78. Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion

79. CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

80. Is Parameter Isolation Better for Prompt-Based Continual Learning?

81. GenSplat: Bridging the Generalization Gap in 3DGS Language Comprehension

82. PhyGaP: Physically-Grounded Gaussians with Polarization Cues

83. FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation

84. OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models

85. Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features

86. Learning Effective Sign Features without Text for Gloss-free Sign Language Translation

87. The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments

88. ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes

89. Contact-Aware Neural Dynamics

90. Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera

91. Globscope: Toward a Global View of the Loss Landscape

92. PG-VTON: Single-Pass Training-Free Virtual Try-On via Patch-Guided Reference Alignment

93. An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

94. Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions

95. Inferring Compositional 4D Scenes without Ever Seeing One

96. Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment

97. ViT3^3: Unlocking Test-Time Training in Vision

98. Elastic Weight Consolidation Done Right for Continual Learning

99. SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation

100. Interpretable and Steerable Concept Bottleneck Sparse Autoencoders

101. pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning

102. Optical Diffraction-based Convolution for Semiconductor Lithography

103. GSNR: Graph Smooth Null-Space Representation for Inverse Problems

104. The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation

105. Beyond Tie Points: Satellite Image Block Adjustment based on Dense Feature Consistency

106. ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization

107. Dynamic Momentum Recalibration in Online Gradient Learning

108. AdaPrior: Bayesian-Inspired Adaptive Prior Correction for Long-Tailed Continual Learning

109. Prompt-Free Universal Region Proposal Network

110. NeuroRule: Bridging Vision and Logic with Differentiable Rule Induction

111. Beyond Single Solution: Multi-Hypothesis Deep Unfolding Network for Image Compressive Sensing

112. MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On

113. Tavatar: Topology-Aware Gaussian Attribute Derivation for Animatable Human Avatars

114. 4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstruction

115. Edit-aware RAW reconstruction

116. HyperST: Hierarchical Hyperbolic Learning for Spatial Transcriptomics Prediction

117. Tunable Soft Equivariance with Guarantees

118. Gated KalmaNet: A Fading Memory Layer through Test-time Ridge Regression

119. Velox: Learning Representations of 4D Geometry and Appearance

120. UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

121. Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation

122. RegionFuse: Region-Adaptive Pixel Distribution Learning for Infrared and Visible Image Fusion

123. TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

124. A Faster Path to Continual Learning

125. Defending Unauthorized Model Merging via Dual-Stage Weight Protection

126. Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning

127. Point4Cast: Streaming Dynamic Scene Reconstruction and Forecasting

128. Spherical Voronoi: Directional Appearance as a Differentiable Partition of the Sphere

129. CHEEM: Continual Learning by Reuse, New, Adapt and Skip - A Hierarchical Exploration-Exploitation Approach

130. Relational Visual Similarity

131. EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models

132. Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization

133. Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training

134. CryoKRAQEN: Kernel-Regularized Annealing for Quantized Embedding Networks in Cryo-EM Heterogeneous Reconstruction

135. Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis

136. ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding

137. Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D

138. Bias at the End of the Score

139. Kaleidoscopic Scintillation Event Imaging

140. Any4D: Unified Feed-Forward Metric 4D Reconstruction

141. It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removal

142. Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts

143. A2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors

144. Gaussian Mapping for Evolving Scenes

145. OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models

146. SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration

147. Coupling Liquid Time-Constant Encoders with Modern Hopfield Memory

148. MA-Bench: Towards Fine-grained Micro-Action Understanding

149. Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras

150. VGGT-Ω

151. CREward: A Type-Specific Creativity Reward Model

152. Solvability of the Viewing Graph Under the Affine Camera Model

153. Efficiency Follows Global-Local Decoupling

154. Designing to Forget: Deep Semi-parametric Models for Unlearning

155. Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared

156. Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

157. Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection

158. ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking

159. Draft and Refine with Visual Experts

160. Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement

161. Closed-Form Concept Erasure via Double Projections

162. Deep Feature Deformation Weights

163. Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Prediction

164. Learning to Solve PDEs on Neural Shape Representations

165. Foundation Encoders Are All You Need for Preference-Aware Personalization

166. MagicQuill V2: Precise and Interactive Image Editing with Layered Visual Cues

167. Reframing Long-Tailed Learning via Loss Landscape Geometry

168. RefTon: Reference person shot assist virtual Try-on

169. Stealing Split Learning Bottom Models by Recovering Embedding Geometry

170. Low-Resolution Editing is All You Need for High-Resolution Editing

171. Visual Personalization Turing Test

172. Hidden Monotonicity: Explaining Deep Neural Networks via their DC Decomposition

173. Linear Fundamental Matrix Estimation from 7 or 5 Points

174. Region-Wise Correspondence Prediction between Manga Line Art Images

175. ALLNet: Multi-task Dense Prediction for Degraded Images

176. FSFSplatter: Geometrically Accurate Reconstruction with Free Sparse-view Images within 2 minutes

177. Modeling Cross-vision Synergy for Unified Large Vision Model

178. A Polynomial Chaos Framework for Causal Discovery in Nonlinear Uncertain Systems

179. FE2E: From Editor to Dense Geometry Estimator

180. Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion

181. Reparameterized Tensor Ring Functional Decomposition for Multi-Dimensional Data Recovery

182. ChordEdit: One-Step Low-Energy Transport for Image Editing

183. Coverage Optimization for Camera View Selection

184. PointCNN++: Performant Convolution on Native Points

185. Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model

186. FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation

187. Hierarchical Process Reward Models are Symbolic Vision Learners

188. Feed-forward Gaussian Registration for Head Avatar Creation and Editing

189. DeDelayed: Deleting Remote Inference Delay via On-Device Correction

190. NTK-Guided Implicit Neural Teaching

191. RefAV: Towards Planning-Centric Scenario Mining

192. GeoCoT: Towards Reliable Remote Sensing Reasoning with Manifold Perspective

193. PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction

194. Coded-E2LF: Coded Aperture Light Field Imaging from Events

195. GeoSANE: Learning Geospatial Representations from Models, Not Data

196. FEAT: Fashion Editing and Try-On from Any Design

197. Learning complete and explainable visual representations from itemized text supervision

198. SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis

199. CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception

200. Towards Training-free Scene Text Editing

201. Modeling the Visual Ambiguity of Human Sketches

202. Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus

203. Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses

204. Beyond Myopic Alignment: Lookahead Optimization for Online Class-Incremental Learning

205. DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

206. Vibe Spaces for Creatively Connecting and Expressing Visual Concepts

207. Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

208. From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

209. RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model

210. Exemplar-Free Continual Learning for State Space Models

211. AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction

212. SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation

213. Convolutional Neural Networks Driven by Content Similarity

214. BiProLoRA: Bilevel Prompt LoRA for Real Scene Recovery

215. Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation

216. Cycle-Consistent Tuning for Layered Image Decomposition

217. Exemplar-Free Class Incremental Learning via Preserving Class-Discriminative Structure

218. AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation

219. SAME: Sparse and Anchored Model Editing for Heterogeneous Incremental Learning under Limited Data

220. DC-Merge: Improving Model Merging with Directional Consistency

221. Random Wins All: Rethinking Grouping Strategies for Vision Tokens

222. Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models

223. Beyond Mimicry: Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations

224. Intrinsic Concept Extraction Based on Compositional Interpretability

225. Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration

226. KaLOS finds Consensus: A Meta-Algorithm for Evaluating Inter-Annotator Agreement in Complex Vision Tasks

227. WRIVINDER: Towards Spatial Intelligence for Geo-locating Ground Images onto Satellite Imagery

228. Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective

229. Seeing without Pixels: Perception from Camera Trajectories

230. SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes

231. TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery

232. Harmonic Canvas: Inversion-Free Editing for Visually-Guided Music Style Transfer

233. HP-Edit: A Human-Preference Post-Training Framework for Image Editing

234. Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment

235. FlashIn: Fast and Accurate Image Inversion for Real-time Image Editing

236. Describe Anything Anywhere At Any Moment

237. Electromagnetic Inverse Scattering from a Single Transmitter

238. Physically-Grounded Turbulence Mitigation with Frame-Shared Degradation Parameters

239. Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs

240. Immunizing Models Against Harmful Long-Horizon Fine-Tuning via Contractive Optimization Dynamics

241. Toward Generalizable Whole Brain Representations with High-Resolution Light-Sheet Data

242. FailureAtlas: Mapping the Failure Landscape of T2I Models via Active Exploration

243. Drainage: A Unifying Framework for Addressing Class Uncertainty

244. High-Fidelity Mobile Avatars with Pruned Local Blendshapes

245. Neural Differentiation in Deep Networks: A Theoretical Framework for Expressivity and Representational Diversity

246. AToken: A Unified Tokenizer for Vision

247. ReLaX: Reasoning with Latent Exploration for Large Reasoning Models

248. LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging

249. Computational Speckle Pattern Interferometry

250. OS-Fed: One Snapshot Is All You Need

251. GeoWorld: Geometric World Models

252. ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps

253. LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction

254. Task-Aware Image Signal Processor for Advanced Visual Perception

255. Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal

256. Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them

257. PhysInOne: Visual Physics Learning and Reasoning in One Suite

258. Thinking with Programming Vision: Towards a Unified View for Thinking with Images

259. IPR-1: Interactive Physical Reasoner

260. VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation

261. Image-based Outlier Synthesis With Training Data

262. Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

263. DuetMerging: Synergizing Dynamic and Static Strategies for Mitigating Task Interference in Model Merging

264. Mixture of Style Experts for Diverse Image Stylization

265. SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL

266. Understanding and Enforcing Weight Disentanglement in Task Arithmetic

267. Learning Eigenstructures of Unstructured Data Manifolds

268. Spectral Mixture-of-Experts for Continual Learning

269. Learning Convex Decomposition via Feature Fields

270. AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts

271. Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation

272. SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Method

273. Motus: A Unified Latent Action World Model

274. Latent Implicit Visual Reasoning

275. Gaze Target Estimation Anywhere with Concepts

276. RaUF: Learning the Spatial Uncertainty Field of Radar

277. FireScope: Wildfire Risk Raster Prediction With a Chain-of-Thought Oracle

278. Fresco: Frequency-Spatial Consistent Optimization for Fine-Grained Head Avatar Modeling

279. HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT

280. VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling

281. Hist2Style: Histogram-Guided Stylization with Bilateral Grids

282. Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors

283. QuadSync: Quadrifocal Tensor Synchronization via Tucker Decomposition

284. ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation

285. Hyperbolic Busemann Neural Networks

286. FVAR: Next-Focus Prediction for Visual Autoregressive Modeling

287. One Algorithm to Align Them All

288. A Mixed Diet Makes DINO An Omnivorous Vision Encoder

289. Pixel2Phys: Distilling Governing Laws from Visual Dynamics

290. Mobile-VTON: High-Fidelity On-Device Virtual Try-On

291. RINO: Rotation-Invariant Non-Rigid Correspondences

292. FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration

293. CountGD++: Generalized Prompting for Open-World Counting

294. From Corners to Fiducial Tags: Revisiting Checkerboard Calibration for Event Cameras

295. GH-NAF: Grid-Adaptive Hash-Level-Attended Neural Attenuation Fields for Discrepancy-Aware CBCT

296. Mapping Networks

297. HQC-NBV: A Hybrid Quantum-Classical View Planning Approach

298. Consensus vs. Controversy: Mapping the Decision Space Where Architectures Diverge

299. The Universal Normal Embedding

300. Through the Frequency Lens: Cross-Domain Generalisable Gaze Estimation with Adaptive Modulation

301. MIBURI: Towards Expressive Interactive Gesture Synthesis

302. Learning Forgery-Aware Lip Representations Without Forgery Priors

303. How to Take a Memorable Picture? Empowering Users with Actionable Feedback

304. ReBaPL: Repulsive Bayesian Prompt Learning

305. Model Merging in the Essential Subspace

306. Virtual Immunohistochemistry Staining with Dual-Aligned Multi-Task Feature Guidance

307. Interactive Episodic Memory with User Feedback

308. Mirror Illusion Art

309. Parallel Rigidity Matters for Bundle Adjustment

310. IMAIA: Interactive Maps AI Assistant for Travel Planning and Geo-Spatial Intelligence

311. RISE: Single Static Radar-based Indoor Scene Understanding

312. OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion

313. Group Editing: Edit Multiple Images in One Go

314. Linking Modality Isolation in Heterogeneous Collaborative Perception

315. Bilevel Layer-Positioning LoRA for Real Image Dehazing

316. PARSE: Part-Aware Relational Spatial Modeling

317. BrepVGAE: Variational Graph Autoencoder with Unified Latent Representation for B-rep

318. Neural Mixture Density Processes

319. Smart Replay: Adaptive Scheduling of Memory Rehearsal for Computational Resource-Aware Incremental Learning

320. SASNet: Spatially-Adaptive Sinusoidal Networks for INRs

321. Cinematic Audio Source Separation Using Visual Cues

322. NeAR: Coupled Neural Asset-Renderer Stack

323. Regulating Rather than Constraining: Adaptive Guidance for Complex Spectral Reconstruction in Pansharpening

324. VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pair

325. Meta-CoT: Enhancing Granularity and Generalization in Image Editing

326. Learning by Analogy: A Causal Framework for Compositional Generalization

327. MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry

328. Measuring the (Un)Faithfulness of Concept-Based Explanations

329. PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis

330. Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging

331. Multi-Scale Gradient-Guided Unrolling Architecture with Adaptive Mamba for Compressive Sensing

332. Dexterous World Models

333. You Only Erase Once: Erasing Anything without Bringing Unexpected Content