MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
hub
Pixtral 12b
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
VT-Bench is the first unified benchmark aggregating 14 visual-tabular datasets with over 756K samples and evaluating 23 models to expose challenges in this multi-modal area.
Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planning to reduce constraint violations by 19.26% and improve task completion.
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
Instruction token embeddings encode visual information that can be leveraged to detect object hallucinations in MLLMs via a new combined score outperforming prior detectors.
Staged post-training with self-distillation lets a 3B omni-modal model match or slightly exceed a 30B model on a visually debiased benchmark.
RadThinking releases a large longitudinal CT VQA dataset stratified into foundation perception questions, single-rule reasoning questions, and compositional multi-step chains grounded in clinical reporting standards for cancer screening.
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
VLMs exhibit a consistent 'Texture Bias Cliff' and fail to comprehend pure geometric shapes from boundary contours alone in zero-shot settings.
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
Vision-language models generate executable Behavior Tree policies for robots from synthetic vision-language data, with successful transfer demonstrated on two real manipulators.
Intermediate layers of a contrastively trained vision-language encoder yield stronger general embeddings than the output layer, enabling state-of-the-art performance across image/video classification, multimodal QA, and dense prediction after simple alignment.
Y-axis features such as major tick digit length, number of ticks, value range, and format introduce significant biases in multimodal models during chart-to-table tasks, with y-axis prompting improving performance for some models.
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
Linear probing reveals a gap between internal representations and responses in LVLMs for visual document understanding, with task information encoded more linearly in intermediate layers than the final layer, and fine-tuning those layers narrows the gap.
DeepSeek-VL2 is a series of MoE vision-language models using dynamic tiling and latent attention that reach competitive or state-of-the-art results on VQA, OCR, document understanding and grounding with 1.0B to 4.5B activated parameters.
Ministral 3 releases 3B/8B/14B parameter-efficient language models with base, instruction, and reasoning variants derived via iterative pruning and distillation, including image understanding capabilities.
Phoenix-VL 1.5 Medium is a 123B-parameter natively multimodal model that reaches state-of-the-art results on Singapore multimodal, legal, and policy benchmarks after localized training on 1T+ tokens while staying competitive on global benchmarks.
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
citing papers explorer
-
Lost in Translation: Do LVLM Judges Generalize Across Languages?
MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
-
VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning
VT-Bench is the first unified benchmark aggregating 14 visual-tabular datasets with over 756K samples and evaluating 23 models to expose challenges in this multi-modal area.
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planning to reduce constraint violations by 19.26% and improve task completion.
-
Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models
Q-Mask uses query-conditioned causal masks to separate text location from recognition in OCR VLMs, backed by a new benchmark and 26M-pair training dataset.
-
Instruction Lens Score: Your Instruction Contributes a Powerful Object Hallucination Detector for Multimodal Large Language Models
Instruction token embeddings encode visual information that can be leveraged to detect object hallucinations in MLLMs via a new combined score outperforming prior detectors.
-
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
Staged post-training with self-distillation lets a 3B omni-modal model match or slightly exceed a 30B model on a visually debiased benchmark.
-
RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology
RadThinking releases a large longitudinal CT VQA dataset stratified into foundation perception questions, single-rule reasoning questions, and compositional multi-step chains grounded in clinical reporting standards for cancer screening.
-
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
-
BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs
VLMs exhibit a consistent 'Texture Bias Cliff' and fail to comprehend pure geometric shapes from boundary contours alone in zero-shot settings.
-
MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
-
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
-
Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision
Vision-language models generate executable Behavior Tree policies for robots from synthetic vision-language data, with successful transfer demonstrated on two real manipulators.
-
Perception Encoder: The best visual embeddings are not at the output of the network
Intermediate layers of a contrastively trained vision-language encoder yield stronger general embeddings than the output layer, enabling state-of-the-art performance across image/video classification, multimodal QA, and dense prediction after simple alignment.
-
Assessing Y-Axis Influence: Bias in Multimodal Language Models on Chart-to-Table Translation
Y-axis features such as major tick digit length, number of ticks, value range, and format introduce significant biases in multimodal models during chart-to-table tasks, with y-axis prompting improving performance for some models.
-
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
-
Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding
Linear probing reveals a gap between internal representations and responses in LVLMs for visual document understanding, with task information encoded more linearly in intermediate layers than the final layer, and fine-tuning those layers narrows the gap.
-
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
DeepSeek-VL2 is a series of MoE vision-language models using dynamic tiling and latent attention that reach competitive or state-of-the-art results on VQA, OCR, document understanding and grounding with 1.0B to 4.5B activated parameters.
-
Ministral 3
Ministral 3 releases 3B/8B/14B parameter-efficient language models with base, instruction, and reasoning variants derived via iterative pruning and distillation, including image understanding capabilities.
-
Phoenix-VL 1.5 Medium Technical Report
Phoenix-VL 1.5 Medium is a 123B-parameter natively multimodal model that reaches state-of-the-art results on Singapore multimodal, legal, and policy benchmarks after localized training on 1T+ tokens while staying competitive on global benchmarks.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.