RoboLab is a new simulation benchmark with 120 tasks across visual, procedural, and relational axes that quantifies generalization gaps and perturbation sensitivity in task-generalist robotic policies.
super hub Mixed citations
PaliGemma: A versatile 3B VLM for transfer
Mixed citation behavior. Most common role is background (59%).
108
Pith papers citing it
Background
59% of classified citations
abstract
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation.
hub tools
citation-role summary
background 19
method 6
baseline 5
dataset 2
citation-polarity summary
claims ledger
- abstract PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model. It is trained to be a versatile and broadly knowledgeable base model that is effective to transfer. It achieves strong performance on a wide variety of open-world tasks. We evaluate PaliGemma on almost 40 diverse tasks including standard VLM benchmarks, but also more specialized tasks such as remote-sensing and segmentation.
authors
co-cited works
representative citing papers
Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
VLA language backbones show high redundancy on manipulation benchmarks, with half the LLM blocks removable and even two blocks sufficient to recover baseline performance after fine-tuning, unlike vision and action pathways.
Koshur Pixel is the first large-scale synthetic OCR dataset for Kashmiri with 613,078 image-text pairs generated via SynthOCR-Gen from the KS-PRET-5M corpus across multiple fonts and granularities with 25+ augmentations.
DeepLatent introduces a parallel latent visual reasoning framework with learnable 2D tokens and continuous RL, trained via distillation then RL, plus a new 180K dataset, claiming SOTA benchmark results.
OmniGF adapts VLMs via dual-branch decoding and head embeddings to unify precise multi-person gaze localization with semantic and social reasoning, claiming new SOTA on benchmarks.
SELECT-LLM is the first active model selection framework for LLMs that uses expected information gain from pairwise output similarities to minimize required annotations, reporting up to 84.78% cost reduction across 23 datasets and 156 models.
GesVLA encodes gesture features directly into the latent space of VLA models using a dual-VLM architecture and a rendering-based data pipeline, yielding improved target grounding in real robotic tasks.
A3 reframes dynamic action chunk commitment in VLA models as self-speculative prefix verification, accepting the longest continuous sequence of actions that satisfies consensus-ordered conditional invariance and prefix-closed sequential consistency.
RIO introduces a lightweight open-source framework that abstracts real-time robot I/O to support easy switching between embodiments and platforms for collecting data and deploying VLAs.
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
AT-VLA proposes adaptive tactile injection and a dual-stream tactile reaction mechanism to enhance VLA models for contact-rich robotic manipulation with real-time responses.
MoSS augments VLAs with decoupled modality streams for multiple physical signals, achieving synergistic gains in real-world robot tasks via joint attention and auxiliary future-signal prediction.
SketchVLM lets VLMs generate non-destructive SVG annotations on input images to visually explain answers, raising visual reasoning accuracy by up to 28.5 points and annotation quality by 1.48x over baselines.
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
DSCA turns concept isolation into an architectural property by dynamically creating orthogonal subspaces for non-interfering lifelong edits in vision-language models, sustaining over 95% success after 1000 sequential edits.
MixAtlas uses CLIP-based decomposition and Gaussian process optimization on small proxies to discover data mixtures that improve multimodal benchmark performance by up to 17.6% and transfer to larger models with faster convergence.
GeCO replaces time-dependent flow matching with time-unconditional optimization, enabling adaptive inference and intrinsic OOD detection for robotic imitation learning.
AR-VLA introduces a standalone autoregressive action expert with long-lived memory that generates context-aware continuous actions for VLAs, replacing chunk-based heads with smoother trajectories and maintained task success.
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
GQR is a test-time optimization technique that refines primary retriever query embeddings using complementary retriever scores to achieve high performance with smaller representations in multimodal visual document retrieval.
SHREC is a new benchmark dataset of embodied human-robot conversations that shows substantial performance gaps in state-of-the-art foundation models on tasks involving social error detection and rationale generation.
VLMs fail at visual counting extrapolation because they cannot project visual magnitudes onto symbolic tokens, despite intact perceptual representations, supporting a fractured magnitude hypothesis.
citing papers explorer
-
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
-
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
Molmo VLMs trained on newly collected PixMo open datasets achieve state-of-the-art performance among open-weight models and surpass multiple proprietary VLMs including Claude 3.5 Sonnet and Gemini 1.5 Pro.
-
Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri
Koshur Pixel is the first large-scale synthetic OCR dataset for Kashmiri with 613,078 image-text pairs generated via SynthOCR-Gen from the KS-PRET-5M corpus across multiple fonts and granularities with 25+ augmentations.
-
DeepLatent: Think with Images via Parallel Latent Visual Reasoning
DeepLatent introduces a parallel latent visual reasoning framework with learnable 2D tokens and continuous RL, trained via distillation then RL, plus a new 180K dataset, claiming SOTA benchmark results.
-
OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
OmniGF adapts VLMs via dual-branch decoding and head embeddings to unify precise multi-person gaze localization with semantic and social reasoning, claiming new SOTA on benchmarks.
-
Dynamic Execution Commitment of Vision-Language-Action Models
A3 reframes dynamic action chunk commitment in VLA models as self-speculative prefix verification, accepting the longest continuous sequence of actions that satisfies consensus-ordered conditional invariance and prefix-closed sequential consistency.
-
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
-
SketchVLM: Vision language models can annotate images to explain thoughts and guide users
SketchVLM lets VLMs generate non-destructive SVG annotations on input images to visually explain answers, raising visual reasoning accuracy by up to 28.5 points and annotation quality by 1.48x over baselines.
-
Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
-
DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
DSCA turns concept isolation into an architectural property by dynamically creating orthogonal subspaces for non-interfering lifelong edits in vision-language models, sustaining over 95% success after 1000 sequential edits.
-
SAM 3: Segment Anything with Concepts
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
-
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
PARCEL is a new visual tokenization architecture combining pool-anchored resampling with conditioned elastic queries to enhance performance-efficiency tradeoffs in LVLMs over prior matryoshka methods.
-
Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning
Inverse dynamics prediction is added as an auxiliary task to reduce state aliasing in VLA models by directly supervising the vision encoder on action-relevant visual distinctions using only standard observation-action pairs.
-
DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
DriveWAM converts video generative priors into a unified video-action policy for driving, reporting strong benchmark performance and positive scaling from 4k to 100k clips.
-
TextTeacher: What Can Language Teach About Images?
TextTeacher uses frozen text embeddings from captions as semantic anchors to guide vision model training, improving ImageNet accuracy by up to 2.7 p.p. and transfer performance by 1.0 p.p. on average.
-
Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
Reweighting training emphasis toward image-negative tokens and filtering hallucinated data reduces object hallucination in LVLMs across three model variants.
-
A More Word-like Image Tokenization for MLLMs
DiVT clusters patch embeddings into coherent semantic units and adapts token count to image complexity, matching or exceeding baselines with fewer visual tokens on multimodal benchmarks.
-
GeoWorld-VLM: Geometry from World Models for Vision-Language Models
GeoWorld-VLM aligns VLM image features with intermediate representations from camera-conditioned world models via fine-tuning only the encoder and projector, yielding ~4% gains on What'sUp and VSR spatial benchmarks across two VLM backbones.
-
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
UAM adds a Dorsal Expert initialized from a generative model and trained on visual dynamics prediction to preserve over 95% of VLM multimodal ability in VLA training while achieving top success rates on manipulation tasks including OOD cases.
-
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
Distills 3D spatial reasoning from a 7B teacher VLM to a 2.29B student using VGGT encoder, multi-task losses, and Hidden CoT latent tokens, yielding 8.7x lower latency with 54-72% performance retention on ScanNet and 3D-FRONT.
-
ViLL-E: Video LLM Embeddings for Retrieval
ViLL-E introduces a dynamic embedding mechanism and joint contrastive-generative training for VideoLLMs, delivering up to 7% gains in temporal localization and 4% in video retrieval while enabling new zero-shot capabilities.
-
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
TIPSv2 improves dense patch-text alignment in vision-language pretraining through distillation and iBOT++ modifications, yielding models on par with or better than recent baselines on 9 tasks across 20 datasets.
-
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.
-
UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
UAV-Track VLA modifies the π0.5 VLA architecture with temporal compression and dual-branch decoding to reach 61.76% success and 269.65 average frames in long-distance pedestrian tracking on a new 890K-frame UAV dataset, while cutting inference latency by 33.4%.
-
Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
Pose-VLA uses a decoupled two-stage pre-training with discrete pose tokens to extract universal 3D spatial priors from 3D datasets and robotic trajectories, achieving 79.5% success on RoboTwin 2.0 and 96.0% on LIBERO.
-
Vision-aligned Latent Reasoning for Multi-modal Large Language Model
VaLR generates vision-aligned latent tokens before each reasoning step to preserve perceptual cues, improving VSI-Bench accuracy from 33.0% to 52.9%.
-
ORCA: An Agentic Reasoning Framework for Hallucination and Adversarial Robustness in Vision-Language Models
ORCA is an agentic reasoning framework that enhances factual accuracy and adversarial robustness of pretrained LVLMs via an Observe-Reason-Critique-Act loop with small vision models, reporting accuracy gains of up to 40% on hallucination benchmarks and 20% under adversarial perturbations.
-
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 average length on CALVIN ABC-D.
-
How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
Multimodal foundation models achieve respectable but sub-specialist performance on semantic vision tasks and weaker results on geometric tasks when evaluated through prompt chaining on established benchmarks.
-
DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving
DriveMoE applies scene-specialized Vision MoE and skill-specialized Action MoE to a VLA baseline to achieve SOTA closed-loop performance on Bench2Drive.
-
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.
-
PILOT: A Promptable Interleaved Layout-aware OCR Transformer
PILOT unifies text recognition, line detection, and promptable extraction in one 155M-parameter generative transformer that outputs interleaved subword and absolute-coordinate tokens on a 10 px grid.
-
Agent Skills Should Go Beyond Text: The Case for Visual Skills
The paper proposes that reusable agent skills should incorporate visual elements alongside text, introduces three forms of visual skills and an automatic conversion system, and reports better performance on GUI and visual-centric tasks.
-
Reinforcement Learning with Robust Rubric Rewards
RLR³ extends RLVR to criterion-level rubric verification via dual execution paths, minimal exposure masking, hierarchical aggregation, and saturation mitigation, delivering 4.7-point gains over base on 15 benchmarks with Qwen3-VL-30B-A3B.
-
DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
DocRetriever introduces a framework using layout-aware sparse embeddings for hybrid encoding without OCR and a generalizable reasoning-augmented reranker for few-shot settings, plus the MultiDocR benchmark for evaluation.
-
SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
SAFE-Pruner forecasts deep-layer token saliency in VLA models via semantic attention consistency and adaptive subtask detection to achieve up to 1.89x speedup with under 1.7% success rate loss.
-
GEM: Generative Supervision Helps Embodied Intelligence
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
-
LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
LVDrive improves closed-loop driving on Bench2Drive by adding latent future scene prediction to VLA models via unified embedding space processing and two-stage trajectory decoding.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
The Amazing Stability of Flow Matching
Flow matching generative models preserve sample quality, diversity, and latent representations despite pruning 50% of the CelebA-HQ dataset or altering architecture and training configurations.
-
Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference
Dual-encoder VLMs gain robust compositional generalization by learning localized alignments from frozen patch and token embeddings instead of using global similarity.
-
LLaVA-OneVision: Easy Visual Task Transfer
LLaVA-OneVision is the first single open LMM to simultaneously achieve strong performance in single-image, multi-image, and video scenarios with cross-scenario transfer capabilities.
-
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
MiniCPM-Llama3-V 2.5 delivers GPT-4V-level multimodal performance on phones through architecture, pretraining, and alignment optimizations.
-
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalization from sparse data.
-
ZAYA1-VL-8B Technical Report
ZAYA1-VL-8B is a new MoE vision-language model with vision-specific LoRA adapters and bidirectional image attention that reports competitive performance against several 3B-4B models on image, reasoning, and counting benchmarks.
-
PLaMo 2.1-VL Technical Report
PLaMo 2.1-VL reports 61.5 ROUGE-L on JA-VG-VQA-500, 85.2% on Japanese Ref-L4, 53.9% zero-shot factory accuracy, and raises anomaly detection F1 from 39.7 to 64.9 after fine-tuning.
-
A Multimodal Depth-Aware Method For Embodied Reference Understanding
A depth-aware multimodal ERU framework with LLM data augmentation and a depth-aware decision module outperforms baselines for referent detection on two datasets.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
-
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
SigLIP 2 models trained with a unified recipe of captioning, self-supervised losses, and curated diverse data outperform prior SigLIP versions on classification, retrieval, localization, dense prediction, and multilingual understanding at scales from 86M to 1B parameters.
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
PaliGemma 2 is a family of vision-language models that achieves state-of-the-art results on transfer tasks like table structure recognition and radiography report generation by combining SigLIP with Gemma 2 models at various sizes and resolutions.