From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
arXiv:2606.26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we…
CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry
arXiv:2606.26538v1 Announce Type: cross Abstract: Deep Transformers are composed of uniformly stacked residual blocks, yet their deepest layers often add…
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
arXiv:2606.25832v2 Announce Type: replace-cross Abstract: Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a…
Detecting and Controlling Sycophancy with Cascading Linear Features
arXiv:2606.26155v1 Announce Type: new Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples…
Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference
arXiv:2606.27090v1 Announce Type: cross Abstract: Global objectives, such as KL divergence and ELBO, are widely used in Bayesian inference for…
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
arXiv:2606.24245v2 Announce Type: cross Abstract: Large language model (LLM) agents increasingly automate complex tasks by integrating language models with external…
UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Understanding in Autonomous Driving
arXiv:2606.24759v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding,…
Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
arXiv:2511.20892v4 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect or outdated content after being employed. Efficient and…
CALIBER: Calibrating Confidence Before and After Reasoning in Language Models
arXiv:2606.24281v1 Announce Type: cross Abstract: Reasoning language models are increasingly asked not only to answer difficult questions, but also to…