Localization in VLMs relies on a containerization mechanism driven by object-aligned tokens and a narrow set of specialized attention heads in early-to-mid or mid-to-late layers.
hub
Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 12roles
background 2polarities
background 2representative citing papers
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
Omni-NegCLIP improves CLIP's negation understanding by up to 52.65% on presence-based and 12.50% on absence-based tasks through front-layer fine-tuning with specialized contrastive losses.
Vision-language models display large performance differences and clear limits in zero-shot country-level geolocalization from ground-view photos, with semantic cues helping coarse guesses but failing on fine details.
A 0.5B student VLM distills from a 3B teacher using visual-switch distillation and DBiLD loss to gain 3.6 points on average across 10 multimodal benchmarks without architecture changes.
RLER trains video-reasoning models with three task-driven RL rewards for evidence production and elects the best answer from a few candidates via evidence consistency scoring, yielding 6.3% average gains on eight benchmarks.
Attention dispersion during extended reasoning impairs MLLM perception on images, and a training-free VRGA framework mitigates it by selecting and reweighting visual attention heads using an entropy-focus criterion.
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
Firebolt-VL introduces an LFM-based decoder and token-grid correlation to achieve linear-time vision-language inference with improved fine-grained grounding.
3D awareness emerges implicitly in MLLMs via self-supervised geometric constraints that create an information bottleneck, removing depth and pose dependencies at inference and cutting latency by 55%.
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.
citing papers explorer
-
Mechanisms of Object Localization in Vision-Language Models
Localization in VLMs relies on a containerization mechanism driven by object-aligned tokens and a narrow set of specialized attention heads in early-to-mid or mid-to-late layers.
-
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
-
Omni-NegCLIP: Enhancing CLIP with Front-Layer Contrastive Fine-Tuning for Comprehensive Negation Understanding
Omni-NegCLIP improves CLIP's negation understanding by up to 52.65% on presence-based and 12.50% on absence-based tasks through front-layer fine-tuning with specialized contrastive losses.
-
Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
Vision-language models display large performance differences and clear limits in zero-shot country-level geolocalization from ground-view photos, with semantic cues helping coarse guesses but failing on fine details.
-
Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
A 0.5B student VLM distills from a 3B teacher using visual-switch distillation and DBiLD loss to gain 3.6 points on average across 10 multimodal benchmarks without architecture changes.
-
Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
RLER trains video-reasoning models with three task-driven RL rewards for evidence production and elects the best answer from a few candidates via evidence consistency scoring, yielding 6.3% average gains on eight benchmarks.
-
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
Attention dispersion during extended reasoning impairs MLLM perception on images, and a training-free VRGA framework mitigates it by selecting and reweighting visual attention heads using an entropy-focus criterion.
-
Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
-
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
-
Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation
Firebolt-VL introduces an LFM-based decoder and token-grid correlation to achieve linear-time vision-language inference with improved fine-grained grounding.
-
3D-IDE: 3D Implicit Depth Emergent
3D awareness emerges implicitly in MLLMs via self-supervised geometric constraints that create an information bottleneck, removing depth and pose dependencies at inference and cutting latency by 55%.
-
TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning
TempR1 applies temporal-aware multi-task RL using GRPO and three types of localization rewards to achieve SOTA temporal understanding in MLLMs with synergistic gains from joint optimization.