arXiv:2605.23111v2 Announce Type: replace Abstract: The human brain represents objects in a way that is both invariant across instances and flexible enough to support different contexts and tasks. Yet it remains unknown how object representations are dynamically remapped as the same object shifts across contextual roles. Here we combined fMRI with naturalistic movie viewing to […]
LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction
arXiv:2603.12647v3 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only for Gaussian initialization or depth supervision, while the rich scene information contained in point clouds, such as reflectance, and […]
Beyond Transfer Accuracy: Faithful Circuits for Controlled Low-Resource Adaptation
arXiv:2601.08146v3 Announce Type: replace-cross Abstract: Existing circuit discovery methods rely on templated tasks with clean counterfactuals, limiting their use on diverse natural text. We adapt Contextual Decomposition for Transformers (CD-T) for unstructured settings via label-balanced activation means and task-directional relevance scoring, enabling counterfactual-free circuit discovery. We leverage these circuits for Circuit-Targeted Supervised Fine-Tuning (CT-SFT), restricting […]
Confounder Detection via Treatment Intent: A New Observational Study Design
arXiv:2605.26413v1 Announce Type: cross Abstract: Understanding the effects of interventions is central to scientific progress, with randomized controlled trials (RCTs) regarded as the gold standard for causal inference in many applied fields. However, RCTs are costly, time-consuming, and often constrained by ethical or practical limitations, motivating the need for causal methods able to draw conclusions […]
Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
arXiv:2605.27078v1 Announce Type: cross Abstract: Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena complicate this picture: in grokking, train loss falls rapidly while test performance improves abruptly only after a long delay; in epoch-wise double descent, train loss decreases monotonically while test loss […]
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
arXiv:2605.26340v1 Announce Type: new Abstract: Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetectable by surface-level evaluation: fabricated citations, unreproducible scores, and method descriptions that diverge from the implementation. We address this through three contributions. First, Chain-of-Evidence (CoE), a verifiability framework requiring every claim to be traceable to […]
Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories
arXiv:2602.12833v2 Announce Type: replace-cross Abstract: Longitudinal clinical reasoning over electronic health records requires tracking evolving physiological measurements, laboratory results, and interventions across extended patient trajectories. Existing LLM-based clinical reasoning systems often rely on repeatedly serializing patient histories or exchanging unconstrained textual agent messages, leading to context drift, unstable reasoning, and growing inference cost over long […]
Automatic Layer Selection for Hallucination Detection
arXiv:2605.26366v1 Announce Type: new Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs). Although a growing body of work has sought to exploit this property for hallucination detection, how to automate the selection of high-performing layers […]
The ATOM Report: Measuring the Open Language Model Ecosystem
arXiv:2604.07190v2 Announce Type: replace-cross Abstract: We present a comprehensive adoption snapshot of the leading open language models and who is building them, focusing on the ~1.5K mainline open models from the likes of Alibaba’s Qwen, DeepSeek, Meta’s Llama, that are the foundation of an ecosystem crucial to researchers, entrepreneurs, and policy advisors. We document a […]
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
arXiv:2605.26371v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counterparts by discovering and reusing temporally-extended skills. However, obtaining skills that are actually reusable remains an open challenge. Towards this end, we focus on abstractions that exploit the intuition of local dynamics: local transitions […]
Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers
arXiv:2605.18106v2 Announce Type: replace-cross Abstract: A striking geometric disparity has long persisted in the practice of deep learning. While modern neural network architectures naturally exhibit rich symmetry and equivariance properties, popular optimizers such as Adam and its variants operate inherently coordinate-wise, rendering them unable to respect the equivariance structures of the parameter space. We address […]
Advancing Creative Physical Intelligence in Large Multimodal Models
arXiv:2605.26396v1 Announce Type: new Abstract: Large multimodal models (LMMs) have rapidly advanced in perception and reasoning; however, it remains unclear whether these capabilities generalize to discovering visually grounded solutions in open-ended environments, beyond pattern recognition. In such settings, intelligence requires more than answering well-posed questions: it involves identifying how elements in a scene can be […]