Reward-guided optimization of SAE latents, gated by reward and confidence, improves multi-benchmark reasoning and is post-hoc associated with more verification and course correction.
arXiv preprint arXiv:2501.15602 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SingGuard introduces a policy-adaptive multimodal LLM guardrail with dynamic reasoning regimes and SingGuard-Bench, reporting SOTA F1 scores across 35 datasets and improved policy-following accuracy under runtime shifts.
A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gains across 15 benchmarks.
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.
citing papers explorer
-
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Reward-guided optimization of SAE latents, gated by reward and confidence, improves multi-benchmark reasoning and is post-hoc associated with more verification and course correction.
-
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
SingGuard introduces a policy-adaptive multimodal LLM guardrail with dynamic reasoning regimes and SingGuard-Bench, reporting SOTA F1 scores across 35 datasets and improved policy-following accuracy under runtime shifts.
-
Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning
A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.
-
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
Early entropy dynamics during LLM decoding mark when explicit reasoning becomes beneficial, enabling the training-free EDRM router that selects strategies per instance and yields 41-55% token savings with accuracy gains across 15 benchmarks.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
-
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.