数据来源：ArXiv Domain LLM Domain Papers1. RedSage: A Cybersecurity Generalist LLMCybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this gap, we curate 11.8B tokens of cybersecurity-focused continual pretraining data via large-scale web filtering and manual collection of high-quality resources, spanning 28.6K docume ...

数据来源：ArXiv Domain LLM Domain Papers1. VideoGPA: Distilling Geometry Priors for 3D-Consistent Video GenerationWhile recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures arise because standard denoising objectives lack explicit incentives for geometric coherence. To address this, we introduce VideoGPA (Video Geometric P ...

数据来源：ArXiv Domain LLM Domain Papers1. Reward-free Alignment for Conflicting ObjectivesDirect alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can lead to unstable training and poor trade-offs. In particular, weighted loss methods may fail to identify update directions that simultaneously improve all objectives, and exis ...

数据来源：ArXiv Domain LLM Domain Papers1. Reinforced Attention LearningPost-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited gains for perception and can even degrade performance. We propose Reinforced Attention Learning (RAL), a policy-gradient framework that directly optimizes internal attention distributions ra ...

数据来源：ArXiv Domain LLM Domain Papers1. EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and InferenceThe rapid growth of large models has raised concerns about their environmental impact and equity in accessibility due to significant computational costs. Low-Rank Adapters (LoRA) offer a lightweight solution for finetuning large models, resulting in an abundance of publicly available adapters tailored to diverse domains. We ask: Can these pretrained ad ...

数据来源：ArXiv Domain LLM Domain Papers1. EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and InferenceThe rapid growth of large models has raised concerns about their environmental impact and equity in accessibility due to significant computational costs. Low-Rank Adapters (LoRA) offer a lightweight solution for finetuning large models, resulting in an abundance of publicly available adapters tailored to diverse domains. We ask: Can these pretrained ad ...

数据来源：ArXiv Domain LLM Domain Papers1. Learning a Generative Meta-Model of LLM ActivationsExisting approaches for analyzing neural network activations, such as PCA and sparse autoencoders, rely on strong structural assumptions. Generative models offer an alternative: they can uncover structure without such assumptions and act as priors that improve intervention fidelity. We explore this direction by training diffusion models on one billion residual stream activations, creating “meta-models” tha ...

数据来源：ArXiv Domain LLM Domain Papers1. Biases in the Blind Spot: Detecting What LLMs Fail to MentionLarge Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these unverbalized biases. Monitoring models via their stated reasoning is therefore unreliable, and existing bias evaluations typically require predefined categories and hand-crafted datasets. In this work, we introduce a fully automated, black-box pipel ...

数据来源：ArXiv Domain LLM Domain Papers1. Diffusion-Pretrained Dense and Contextual EmbeddingsIn this report, we introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone for web-scale retrieval. By leveraging bidirectional attention through diffusion-based pretraining, our models capture comprehensive bidirectional context within passages, enabling the use of mean pooling and a late chunking strat ...

数据来源：ArXiv Domain LLM Domain Papers1. Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action AlignmentThe long-standing vision of general-purpose robots hinges on their ability to understand and act upon natural language instructions. Vision-Language-Action (VLA) models have made remarkable progress toward this goal, yet their generated actions can still misalign with the given instructions. In this paper, we investigate test-time verification as a m ...

数据来源：ArXiv Domain LLM Domain Papers1. Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action AlignmentThe long-standing vision of general-purpose robots hinges on their ability to understand and act upon natural language instructions. Vision-Language-Action (VLA) models have made remarkable progress toward this goal, yet their generated actions can still misalign with the given instructions. In this paper, we investigate test-time verification as a m ...

数据来源：ArXiv Domain LLM Domain Papers1. Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action AlignmentThe long-standing vision of general-purpose robots hinges on their ability to understand and act upon natural language instructions. Vision-Language-Action (VLA) models have made remarkable progress toward this goal, yet their generated actions can still misalign with the given instructions. In this paper, we investigate test-time verification as a m ...

数据来源：ArXiv Domain LLM Domain Papers1. Semantic Chunking and the Entropy of Natural LanguageThe entropy rate of printed English is famously estimated to be about one bit per character, a benchmark that modern large language models (LLMs) have only recently approached. This entropy rate implies that English contains nearly 80 percent redundancy relative to the five bits per character expected for random text. We introduce a statistical model that attempts to capture the intricate multi-scale str ...

数据来源：ArXiv Domain LLM Domain Papers1. Symmetry in language statistics shapes the geometry of model representationsAlthough learned representations underlie neural networks’ success, their fundamental properties remain poorly understood. A striking example is the emergence of simple geometric structures in LLM representations: for example, calendar months organize into a circle, years form a smooth one-dimensional manifold, and cities’ latitudes and longitudes can be decoded by a linear probe. ...

数据来源：ArXiv Domain LLM Domain Papers1. Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion MatchingWhile recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex environments demands not only low-level robustness, but also human-like motion expressiveness, long-horizon skill composition, and perception-driven dec ...