pith. sign in

In: The Thirteenth International Conference on Learning Representations (2025)

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

clear filters

representative citing papers

HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization

cs.CV · 2026-04-22 · conditional · novelty 6.0 · 2 refs

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.

How Far Are Video Models from True Multimodal Reasoning?

cs.CV · 2026-04-21 · unverdicted · novelty 6.0

Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.

citing papers explorer

Showing 2 of 2 citing papers after filters.

  • HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization cs.CV · 2026-04-22 · conditional · none · ref 40 · 2 links

    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.

  • How Far Are Video Models from True Multimodal Reasoning? cs.CV · 2026-04-21 · unverdicted · none · ref 80

    Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.