Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2508. 12116v2 Announce Type: replace-cross Abstract: As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge.
arXiv:2606. 27806v3 Announce Type: replace Abstract: Language agents plan by generating not only actions but also implicit predictions of how the world will change.
arXiv:2509. 23960v2 Announce Type: replace-cross Abstract: Co-optimizing safety and performance in large-scale multi-agent systems remains a fundamental challenge.
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
arXiv:2607. 03065v1 Announce Type: cross Abstract: Reinforcement learning has become a standard post-training recipe for large language models, but dense full-parameter updates create two deployment-relevant bottlenecks: suppressed reasoning performance, often reflected by premature saturation of test-time scaling, and interference when consolidating multiple capabilities through multi-domain training or model merging.
arXiv:2607. 03109v1 Announce Type: cross Abstract: We study a graph classification problem involving over 20 million graphs, arising from high-order perturbative computations of correlators in planar $\mathcal{N}=4$ super-Yang--Mills, a model closely related to the theory of the strong nuclear force.
arXiv:2607. 02575v1 Announce Type: cross Abstract: Vision-language models can perform new tasks without parameter updates through in-context learning (ICL), whose core mechanism is utilizing the support set for task induction.
arXiv:2605. 17758v2 Announce Type: replace Abstract: Synthetic data is widely used in healthcare to create datasets that preserve statistical properties of real data without exposing sensitive patient information.
arXiv:2607. 03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason.
arXiv:2607. 04478v1 Announce Type: cross Abstract: Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features in conventional architectures.
arXiv:2607. 04661v1 Announce Type: cross Abstract: Reconstructing 3D scene structures from sparse, low-overlap observations remains a fundamental challenge in autonomous driving.
arXiv:2507. 04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates.
arXiv:2607. 03073v1 Announce Type: cross Abstract: Criminal identification from surveillance imagery has become a critical research area in intelligent forensic surveillance systems due to the increasing deployment of CCTV cameras in public and private environments.
arXiv:2607. 05199v1 Announce Type: new Abstract: Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows.
arXiv:2607. 03998v1 Announce Type: new Abstract: The local sharpness of the loss, the top Hessian eigenvalue $\lambda_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or Hessian-vector iterations.
arXiv:2607. 05188v1 Announce Type: new Abstract: A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on.
arXiv:2607. 02608v1 Announce Type: cross Abstract: Lightweight neuromorphic computing offers a promising route to efficient AI, with particular benefits for resource-constrained edge deployments.
arXiv:2607. 04990v1 Announce Type: new Abstract: This work delivers two key contributions: one to efficient feature selection in reinforcement learning (RL), the other to the theory of non-monotone inclusions.
arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.
arXiv:2607. 05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs.