DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
super hub Mixed citations
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Mixed citation behavior. Most common role is background (57%).
146
Pith papers citing it
Background
57% of classified citations
abstract
We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.
hub tools
citation-role summary
background 21
baseline 10
method 3
dataset 2
other 1
citation-polarity summary
claims ledger
- abstract We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capabili
authors
co-cited works
representative citing papers
MMRareBench provides 1,756 QA pairs and 7,958 images from PMC rare-disease cases to evaluate 23 MLLMs, revealing low treatment-planning scores and medical models underperforming general models on multi-image tasks due to capacity dilution.
HM-Bench is the first benchmark for MLLMs on hyperspectral images, showing models struggle with complex spatial-spectral reasoning and perform better with visual PCA images than textual reports.
DDIPE poisons LLM agent skills by embedding malicious logic in documentation examples, achieving 11.6-33.5% bypass rates across frameworks while explicit attacks are blocked, with 2.5% evading detection.
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.
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
MuseBench shows state-of-the-art MLLMs achieve only 48.29% accuracy on intent-level audiovisual arts understanding versus 87.18% for human experts.
SpreadsheetBench 2 provides 321 expert-validated tasks from authentic business data showing frontier LLMs reach only 34.89% overall accuracy on end-to-end spreadsheet workflows.
PRCR enables replay-free visual revisiting in interleaved multimodal reasoning by storing raw visual KV caches with spatial coordinates and rebinding keys to position-compatible coordinates, matching replay performance while cutting computation by orders of magnitude.
JudgeFit produces per-VLM physical video evaluation taxonomies that improve held-out accuracy by a mean 32% relative to a single global schema across 16 models from eight families.
CheXpercept is a sequential multi-level perception benchmark showing VLMs perform adequately only on coarse lesion detection in chest X-rays while degrading sharply on finer tasks, with medical VLMs offering no advantage over general models.
PorTEXTO benchmark shows sharp real-world performance drops in pt-PT OCR and finds specialized multilingual data outperforms model size or resolution increases.
FORGE benchmark shows search-augmented LLMs recommend fake products at rates up to 27% from one polluted page and 73.8% from top-3 replacement across 12 models and 225 products.
SpatialWorld is a new multi-simulator benchmark showing top multimodal agents achieve under 18% success on interactive spatial tasks requiring active exploration and long-horizon planning.
NutriMLLM models fine-tuned on 1.1 million synthetic food image-nutrient triplets from population dietary recalls achieve near-complete coverage and competitive accuracy on real food images for comprehensive micronutrient estimation compared to proprietary MLLMs.
UltraVR is a new diagnostic benchmark for evidence-grounded VQA on ultra-resolution images, with structured chain-of-thought annotations that localize failures in grounding, perception, and inference.
FindIt is the first comprehensive benchmark for evaluating generalist MLLMs on promptable object detection, referring expression detection, instance-level detection, and video detection with standardized parsable outputs.
VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
Moment-Video benchmark shows top video MLLM achieves only 39.6% accuracy on momentary visual event tasks, with most open-source models below 25%.
ChartArena is a new benchmark dataset and evaluation protocol for chart parsing by MLLMs that covers numeric and diagrammatic charts in multiple languages and real-world visual conditions.
MM-Snowball benchmark diagnoses hallucination snowballing in multi-turn MLLM dialogues; CAVR mitigates it via dual visual rectification at representation and logit levels.
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.
StemBind benchmark diagnoses MLLM failures in abstract visual reasoning by separating perception, rule induction, and answer selection on shared stems, finding a persistent rule-to-instance binding gap even when perception and rule are correct.
citing papers explorer
-
RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management
RiskWebWorld is the first realistic interactive benchmark for GUI agents in e-commerce risk management, revealing a large gap between generalist and specialized models plus RL gains.