arXiv:2601.19094v1 Announce Type: cross Abstract: Developing models capable of complex, multi-step reasoning is a central goal in artificial intelligence. While representing problems as graphs is a powerful approach, Graph Neural Networks (GNNs) are fundamentally constrained by their message-passing mechanism, which imposes a local bottleneck that limits global, holistic reasoning. We argue that dynamic programming (DP), […]
LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems
arXiv:2601.19121v1 Announce Type: cross Abstract: Recommendation systems must optimize multiple objectives while satisfying hard business constraints such as fairness and coverage. For example, an e-commerce platform may require every recommendation list to include items from multiple sellers and at least one newly listed product; violating such constraints–even once–is unacceptable in production. Prior work on multi-objective […]
GPCR-Filter: a deep learning framework for efficient and precise GPCR modulator discovery
arXiv:2601.19149v1 Announce Type: cross Abstract: G protein-coupled receptors (GPCRs) govern diverse physiological processes and are central to modern pharmacology. Yet discovering GPCR modulators remains challenging because receptor activation often arises from complex allosteric effects rather than direct binding affinity, and conventional assays are slow, costly, and not optimized for capturing these dynamics. Here we present […]
SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing
arXiv:2601.19180v1 Announce Type: cross Abstract: Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines. However, existing approaches rely on fixed Gaussian noise to construct the source trajectory, leading to biased trajectory dynamics and causing structural degradation or quality loss. To address this, we introduce SNR-Edit, a training-free framework achieving faithful Latent Trajectory […]
Optimal Scaling Needs Optimal Norm
arXiv:2510.03871v2 Announce Type: replace-cross Abstract: Despite recent progress in optimal hyperparameter transfer under model and dataset scaling, no unifying explanatory principle has been established. For Adam and Scion optimizers, we discover that joint optimal scaling across model and dataset sizes is conditioned on a single invariant: the operator norm of the output layer. Across models […]
UniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspection
arXiv:2601.19222v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) show promise for general industrial quality inspection, but fall short in complex scenarios, such as Printed Circuit Board (PCB) inspection. PCB inspection poses unique challenges due to densely packed components, complex wiring structures, and subtle defect patterns that require specialized domain expertise. However, a high-quality, […]
Curiosity Driven Knowledge Retrieval for Mobile Agents
arXiv:2601.19306v1 Announce Type: new Abstract: Mobile agents have made progress toward reliable smartphone automation, yet performance in complex applications remains limited by incomplete knowledge and weak generalization to unseen environments. We introduce a curiosity driven knowledge retrieval framework that formalizes uncertainty during execution as a curiosity score. When this score exceeds a threshold, the system […]
FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Geometry-Complete 4D Reconstruction
arXiv:2601.18993v1 Announce Type: cross Abstract: Camera redirection aims to replay a dynamic scene from a single monocular video under a user-specified camera trajectory. However, large-angle redirection is inherently ill-posed: a monocular video captures only a narrow spatio-temporal view of a dynamic 3D scene, providing highly partial observations of the underlying 4D world. The key challenge […]
DSSmoothing: Toward Certified Dataset Ownership Verification for Pre-trained Language Models via Dual-Space Smoothing
arXiv:2510.15303v4 Announce Type: replace-cross Abstract: Large web-scale datasets have driven the rapid advancement of pre-trained language models (PLMs), but unauthorized data usage has raised serious copyright concerns. Existing dataset ownership verification (DOV) methods typically assume that watermarks remain stable during inference; however, this assumption often fails under natural noise and adversary-crafted perturbations. We propose the […]
Text2Grad: Reinforcement Learning from Natural Language Feedback
arXiv:2505.22338v2 Announce Type: replace-cross Abstract: Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent work augments RL with textual critiques through prompting or reflection, improving interpretability but leaving model parameters untouched. We introduce Text2Grad, a reinforcement-learning paradigm that turns […]
SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
arXiv:2506.22506v2 Announce Type: replace-cross Abstract: Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients. However, the security implications of this setup remain underexplored. In this work, we present the first study of backdoor attacks in Federated Prompt Learning. We show that when malicious […]
LvD: A New Algorithm for Computing the Likelihood of a Phylogeny
arXiv:2601.19064v1 Announce Type: new Abstract: There are few, if any, algorithms in statistical phylogenetics which are used more heavily than Felsenstein’s 1973 pruning method for computing the likelihood of a tree. We present LvD, (Likelihood via Decomposition), an alternative to Felsenstein’s algorithm based on a different decomposition of the underlying phylogeny. It works for all […]