DRAPE generates query-image conditioned prompts on the fly for multimodal continual instruction tuning and reports SOTA results on MCIT benchmarks.
hub Baseline reference
Clevr-math: A dataset for compositional language, visual and mathematical reasoning
Baseline reference. 57% of citing Pith papers use this work as a benchmark or comparison.
13
Pith papers citing it
Baseline
57% of classified citations
hub tools
citation-role summary
dataset 4
background 3
citation-polarity summary
representative citing papers
Staged post-training that first solidifies visual perception before visual and textual reasoning improves VLM accuracy and shortens reasoning traces on visual math and perception benchmarks.
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
UEC-RL improves RL reasoning performance in LLMs and VLMs by activating exploration on hard prompts and stabilizing entropy, delivering a 37.9% relative gain over GRPO on Geometry3K.
MAny addresses dual-forgetting in multimodal continual instruction tuning via CPM and LPM merging strategies, delivering up to 8.57% accuracy gains on UCIT benchmarks without additional training.
Conformal prediction adapted to reasoning-answer pairs in LRMs yields distribution-free uncertainty sets with finite-sample guarantees, paired with a Shapley explanation method that isolates provably sufficient training subsets and steps.
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
InternLM-XComposer-2.5 is a 7B vision-language model supporting up to 96K context that reaches GPT-4V-level performance on image, video, and multi-turn tasks and adds LoRA-driven text-image composition capabilities.
Vision-EKIPL injects high-quality actions from external models into RL training to expand exploration and raise the reasoning ceiling of MLLMs, reporting up to 5% gains on the Reason-RFT-CoT benchmark.
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
citing papers explorer
-
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
Staged post-training that first solidifies visual perception before visual and textual reasoning improves VLM accuracy and shortens reasoning traces on visual math and perception benchmarks.
-
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
-
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.