arXiv AI
Jun 30
IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting
arXiv:2606. 30024v1 Announce Type: cross Abstract: Recent advances in deep learning have notably improved steganographic message hiding.
Fine-tuning and adaptation
LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv AI
Jun 30
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
arXiv:2606. 30266v1 Announce Type: cross Abstract: Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M).
Hugging Face Trending Papers
Jun 29
Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these communities, which affects international collaboration and the progress of sustainability-related research.
Hugging Face Trending Papers
Jun 29
Defending Against Harmful Supervision Hidden in Benign Samples
Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign tasks. We propose Embedded Attack, where harmful QA pairs are embedded within benign training samples, and show that representative guardrails often fail to detect them at the example level.
Hugging Face Trending Papers
Jun 29
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical reasoning required for scientific imagery. Inspired by Peirce's Semiotic Triad, we introduce Scientific Image Reasoning (SciIR), a comprehensive resource for training and evaluation of scientific image generation.
Hugging Face Trending Papers
Jun 29
Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces. Instead of treating Low-Rank Adaptation (LoRA) modules as disposable per-task adapters, NSR manages them as compressible, retrievable memory units on a frozen backbone through a recurring cycle: (1) compress learned LoRAs via SVD, (2) reserve them in a TaskKnowledgeBank, (3) recall related past LoRAs by embedding similarity to warm-start new or returning tasks, and (4) reallocate the active subspace accordingly, with distillation protecting prior tasks.
Hugging Face Trending Papers
Jun 29
Parametric Skills
Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted from task trajectories, are textual recipes encoding mature problem-solving experience and are critical to agentic capabilities.
arXiv AI
Jun 29
Parameter Efficient Hybrid Transformer (PEHT) for Network Traffic Prediction via Dynamic Urban Congestion Integration
arXiv:2606. 28274v1 Announce Type: cross Abstract: Accurate network traffic prediction is a critical element for efficient resource allocation in dynamic urban cellular networks.
arXiv AI
Jun 29
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
arXiv:2606. 25034v2 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety.
arXiv AI
Jun 29
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
arXiv:2606. 27755v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds what is needed for short robotic instructions.
arXiv AI
Jun 29
KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems
arXiv:2606. 27742v1 Announce Type: cross Abstract: Enterprise Knowledge Graphs (KGs) are increasingly used for internal search, analytics, and question answering, but building natural-language interfaces for private enterprise graphs remains costly.
arXiv AI
Jun 29
Two-Stage Fine-Tuning for Protein Sequence Generation with Targeted Amino-Acid Composition
arXiv:2606. 27939v1 Announce Type: cross Abstract: Protein language models are standard priors for biological sequence generation, but steering them toward explicit distributional design targets remains largely unexplored.
arXiv AI
Jun 29
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning
arXiv:2511. 20196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training.
arXiv AI
Jun 29
The Context-Ready Transformer
arXiv:2606. 27538v1 Announce Type: cross Abstract: We introduce the context-ready transformer, a new recurrent neural network architecture built from a D-layer transformer block that pre-contextualizes each token before it enters the block.
arXiv Machine Learning
Jun 29
Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting
arXiv:2510. 00809v3 Announce Type: replace Abstract: While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood.
arXiv Machine Learning
Jun 29
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
arXiv:2510. 18874v3 Announce Type: replace Abstract: Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting.
arXiv Machine Learning
Jun 29
EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography
arXiv:2606. 28164v1 Announce Type: cross Abstract: Echocardiography is the most widely used non-invasive cardiac imaging modality, providing essential information for cardiovascular diagnosis.
arXiv Machine Learning
Jun 29
Physics-Informed Neural Network with Transfer Learning for State Estimation in Lithium-Ion Batteries using the Single Particle Model with Electrolyte
arXiv:2606. 28220v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving nonlinear partial differential equations (PDEs), including battery electrochemical models.
arXiv Machine Learning
Jun 29
Qwen-Image-2.0-RL Technical Report
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
arXiv Machine Learning
Jun 29
FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.