Computer Science

Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders

Do VLMs Need Vision Transformers? Evaluating S...

Computer Vision and Pattern Recognition
Avatar
librarian
4 views
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Avatar
librarian
6 views
SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues

SAVeS: Steering Safety Judgments in Vision-Lan...

Computer Vision and Pattern Recognition
Avatar
librarian
6 views
How Uncertainty Estimation Scales with Sampling in Reasoning Models
Avatar
librarian
13 views
DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

DreamPartGen: Semantically Grounded Part-Level...

Computer Vision and Pattern Recognition
Avatar
librarian
7 views
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Avatar
librarian
14 views
D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding
Avatar
librarian
11 views
cuGenOpt: A GPU-Accelerated General-Purpose Metaheuristic Framework for Combinatorial Optimization
Avatar
Yuyang Liu
11 views
Box Maze: A Process-Control Architecture for Reliable LLM Reasoning
Avatar
Zou Qiang
11 views
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
Avatar
Masoumeh Shafieinejad
9 views
dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
Avatar
librarian
12 views
MANAR: Memory-augmented Attention with Navigational Abstract Conceptual Representation
Avatar
librarian
11 views
Memento-Skills: Let Agents Design Agents
Avatar
librarian
33 views
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation
Avatar
librarian
11 views
CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
Avatar
librarian
6 views
Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory
Avatar
Oliver Zahn
10 views