LARC enables continuous latent reasoning for multimodal image generation
LARC uses curriculum SFT and information-gain RL to bridge discrete token and continuous image spaces, delivering 7% GenEval gains and test-time scaling.
Stories per day · 30 days
1 RSS
Relatedllm-agents2multimodal2reinforcement-learning2arxiv1continuous-space1gpt1image-generation1multi-agent1test-time-scaling1theory-of-mind1
13 stories, newest first · one card per story
Stories tagged #latent-reasoning
LARC advances continuous-space reasoning in multimodal models
LARC reasons over continuous hidden states to fix token bottlenecks, boosting image generation quality and test-time scaling on GenEval.
ToM2Vec learns continuous theory-of-mind tokens for agents
Latent tokens conditioned thoughts and actions and transferred to unseen partner models, including GPT-5.4.
Hybrid Reasoning Agents think in latent space, act in text
The Hacker News feed links arXiv 2610.18861 but includes no abstract, methods, or results.
Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
LatentGRM judges preferences in compressed latent space, cutting 8B judge time about 6–7x while matching SFT accuracy.
Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Painter-Thinker adds recursive latent reasoning to diffusion, solving 92.5% of hard MNIST Sudoku puzzles.
What Matters for Latent Reasoning with Flow Matching
FLaRe flow-matching latent reasoning reaches 97% of explicit CoT accuracy at quarter latency.
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Scaffolding Minds lifts latent multimodal reasoning by 5.6 points across nine visual benchmarks.
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
ReaLVR adds visual-evidence supervision to latent reasoning, hitting 63.7% on Qwen2.5-VL-7B and scaling to 235B.
A Princeton Researcher Proposes Recurrent Looped Transformer (RLT) that Carries Decoder State across Every Token, Fixing 96 Blocks per Token with Unbounded Temporal Depth
Princeton researcher Yifan Zhang proposes Recurrent Looped Transformer, carrying full decoder state across every token for unbounded temporal depth.
4
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
A*-Thought-V2 compresses redundant chain-of-thought steps into latent tokens guided by hidden-state geometry, improving accuracy up to 2.6% while halving response length.
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
A*-Thought-V2 compresses chain-of-thought into latent tokens using geometric hidden-state dynamics, cutting computation while improving accuracy on Qwen models.
Reason Through the Latent! Making Latent Visual Reasoning Necessary
Researchers introduce CVRR, forcing multimodal models to rely on recurrent latent computation rather than accessible image tokens, validated via causal interventions and benchmarks.