Paper page - PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
… Elastic visual-token compression addresses this by training a single model that can run at multiple visual-token budgets . …
Search
Related topics:
Elastic
Tracked topic
Elastic
Paper page - Who Prices Cognitive Labor in the Age of Agents? Compute-Anchored Wages
… Once this is recognized, the elastic-supply margin that anchors the equilibrium wage migrates from the labor market to the compute capital market. …
Paper page - FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct We present a novel formulation for mesh-free , reduced-order simulation of deformable hyperelastic objects. …
Paper page - PhysiFormer: Learning to Simulate Mechanics in World Space
… Given the initial vertex positions and velocities, as well as object material type, rigid or elastic, the model samples future vertex trajectories . …
Paper page - HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing
… The following papers were recommended by the Semantic Scholar API CoReDiT: Spatial Coherence-Guided Token Pruning and Reconstruction for Efficient Diffusion Transformers 2026 ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generat… …
Paper page - EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct Humans naturally understand object physics through everyday interactions, but faithfully predicting complex deformable dynamics, such as elastic materials and fabrics, remains a major challenge for computer vision and robotics. …
Paper page - Vision Pretraining for Dense Spatial Perception
… The following papers were recommended by the Semantic Scholar API ViT-Up: Faithful Feature Upsampling for Vision Transformers 2026 Learning to Perceive"Where": Spatial Pretext Tasks for Robust Self-Supervised Learning 2026 You Don't Need Strong Assumptions: Visual Representation Learning via Tempor… …
Paper page - Phase Marginalization for Patch-Grid Instability in Vision Transformers
… The following papers were recommended by the Semantic Scholar API Elastic Attention Cores for Scalable Vision Transformers 2026 Token-Space Mask Prediction for Efficient Vision Transformer Segmentation 2026 PaceVGGT: Pre-Alternating-Attention Token Pruning for Visual Geometry Transformers 2026 TALO… …
Paper page - MemTrain: Self-Supervised Context Memory Training
… The following papers were recommended by the Semantic Scholar API InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain 2026 Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents 2026 Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented… …
Paper page - XSkill: Continual Learning from Experience and Skills in Multimodal Agents
… The following papers were recommended by the Semantic Scholar API AutoRefine: From Trajectories to Reusable Expertise for Continual LLM Agent Refinement 2026 AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios 2026 SkillRL: Evolving Agents via Recursive Skill-Au… …