Future-L1 interleaves latent visual spans with text in MLLM decoding, trained on a custom Future-L1-50K dataset via LA-DAPO RL, and reports SOTA gains on FutureBench (61.0 to 85.4) and TwiFF-Bench (2.44 to 3.04).
Sketch-in-latents: Eliciting unified reasoning in mllms.arXiv preprint arXiv:2512.16584
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
baseline 2
background 1
citation-polarity summary
years
2026 8representative citing papers
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.
UniVLR unifies textual and visual reasoning in multimodal LLMs by compressing reasoning traces and auxiliary images into visual latent tokens for direct inference without interleaved text CoT.
Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
ReGuLaR is a relation-grounded latent reasoning method for LVLMs that trains with a ReGFormer on a new RGROUNDING-351K dataset to achieve SOTA benchmark performance while running without the module at inference.
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
HyLaR interleaves discrete text generation with continuous visual latent representations and optimizes them via a decoupled RL algorithm using vMF distributions, improving fine-grained visual reasoning.
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
citing papers explorer
-
Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction
Future-L1 interleaves latent visual spans with text in MLLM decoding, trained on a custom Future-L1-50K dataset via LA-DAPO RL, and reports SOTA gains on FutureBench (61.0 to 85.4) and TwiFF-Bench (2.44 to 3.04).
-
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.
-
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
UniVLR unifies textual and visual reasoning in multimodal LLMs by compressing reasoning traces and auxiliary images into visual latent tokens for direct inference without interleaved text CoT.
-
Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
-
ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language Models
ReGuLaR is a relation-grounded latent reasoning method for LVLMs that trains with a ReGFormer on a new RGROUNDING-351K dataset to achieve SOTA benchmark performance while running without the module at inference.
-
Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
-
HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
HyLaR interleaves discrete text generation with continuous visual latent representations and optimizes them via a decoupled RL algorithm using vMF distributions, improving fine-grained visual reasoning.
-
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.