VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
Lora: Low-rank adaptation of large language models.Iclr, 1(2):3
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
method 2polarities
use method 2representative citing papers
VISAFF is a tuning-free speaker-centered visual affective feature learning framework for emotion recognition in conversation that guides frozen VLMs to active speakers and uses reliability-guided complementation from textual and acoustic modalities to achieve competitive performance.
VideoRLVR uses SDE-GRPO optimization, dense decomposed rewards, and Early-Step Focus to train video diffusion models on verifiable reasoning tasks, outperforming supervised fine-tuning and other video generators on Maze, FlowFree, and Sokoban.
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
citing papers explorer
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation
VISAFF is a tuning-free speaker-centered visual affective feature learning framework for emotion recognition in conversation that guides frozen VLMs to active speakers and uses reliability-guided complementation from textual and acoustic modalities to achieve competitive performance.
-
Video Models Can Reason with Verifiable Rewards
VideoRLVR uses SDE-GRPO optimization, dense decomposed rewards, and Early-Step Focus to train video diffusion models on verifiable reasoning tasks, outperforming supervised fine-tuning and other video generators on Maze, FlowFree, and Sokoban.
-
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.