arXiv AI
Jul 7
Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding
arXiv:2606. 13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress.
Iterative Visual Thinking: Teaching Vision-Language Models Spatial Self-Correction through Visual Feedback
arXiv:2606. 13156v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong singleshot spatial grounding, yet lack any mechanism to observe and correct their own predictions.
Related stories
arXiv Machine Learning
Jul 28
Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
arXiv:2607. 23125v1 Announce Type: new Abstract: Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks.
arXiv AI
Jun 16
Thinking with Visual Grounding
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
arXiv AI
2d ago
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...
arXiv Computer Vision
4d ago
Spatial-OPSD: Self-Improving Spatial Reasoning via Label-Free Self-Distillation
Spatial-OPSD is a label‑free self‑improvement framework for vision‑language models that leverages spatial priors such as depth, 3D relations, and camera geometry to provide dense token‑level supervision. During training, a privileged teacher uses these priors while the student learns from only the original visual‑language input, and a recursive round‑wise scheme allows repeated self‑improvement without moving the teacher. Across four VLM families, one round of Spatial‑OPSD improves the five‑benchmark average, and three rounds push a strong spatially specialized model to the open‑source frontier, achieving the highest average among open models and best results on three of five spatial reasoning benchmarks.
arXiv Computer Vision
Sep 16
SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation
SAVOR is a training framework for multimodal large language models that adds token and answer confidence to the output schema, optimises a Group Relative Policy Optimisation objective to penalise calibration error and poor abstention, and uses the learned confidence at inference to revisit visual evidence only when uncertain. Experiments on POPE, HallusionBench, AMBER, and MMHal-Bench with InternVL3-8B and Qwen3-VL-8B backbones show that SAVOR reduces hallucination while maintaining general capability on MME and MMBench, achieving lower Expected Calibration Error than DPO and decoding baselines.
arXiv Machine Learning
Jun 5
Learning Self-Correction in Vision-Language Models via Rollout Augmentation
arXiv:2602. 08503v2 Announce Type: replace-cross Abstract: Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs).
Hugging Face Trending Papers
Jun 4
Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation
While vision-language models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this to a perception-reasoning modality gap: visual planning requires models to infer latent state structures from pixels and then reason over the recovered structure to produce valid actions, whereas symbolic planning directly leverages explicit objects and constraints.
arXiv AI
Jun 12
Foresight: Iterative Reasoning About Clues that Matter for Navigation
arXiv:2606. 12550v1 Announce Type: cross Abstract: Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal.
Hugging Face Trending Papers
Aug 10
Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots
Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Distillation offers a richer alternative through dense token-level supervision, but in the visual domain it usually depends on privileged context constructed using external annotations and tools, or stronger models.
arXiv AI
3d ago
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
GroundingPI is a 4‑billion‑parameter grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. It is trained with multimodal and spatial pretraining, supervised fine‑tuning, and reinforcement learning, achieving a new state‑of‑the‑art average of 73.68% across 34 grounding benchmarks. As a visual backbone, GroundingPI improves performance in robotic manipulation and autonomous driving, outperforming larger models and mainstream backbones in several out‑of‑distribution settings.
Hugging Face Trending Papers
Sep 15
SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation
Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that...