Top Conference Papers

Concept Arithmetics for Circumventing Concept Inhibition in Difusion Models

Minimalist Vision with Freeform Pixels

NITROGEN: An Open Foundation Model for Generalist Gaming Agents

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time

Navigation World Models

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

3D Student Splatting and Scooping

VGGT: Visual Geometry Grounded Transformer

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

EventPS: Real-Time Photometric Stereo Using an Event Camera

Rich Human Feedback for Text-to-Image Generation

Generative Image Dynamics

SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency

Objects as volumes: A stochastic geometry view of opaque solids

Mip-Splatting: Alias-free 3D Gaussian Splatting

Image Processing GNN: Breaking Rigidity in Super-Resolution

Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods

BIOCLIP: A Vision Foundation Model for the Tree of Life

ViLL-E: Video LLM Embeddings for Retrieval

Systematicity between Forms and Meanings across Languages Supports Efficient Communication

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning

MAUBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery

Massively Multilingual Joint Segmentation and Glossing

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage

Hierarchical Intelligent Acoustic-Semantic Modeling: Modality Separation and Alignment for Full-Duplex SLMs

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models

Evolutionary Guided Decoding: Iterative Value Refinement for LLMs