WaterVIB: Learning Minimal Sufficient Watermark Representations via Variational Information Bottleneck
arXiv:2602.21508v1 Announce Type: new Abstract: Robust watermarking is critical for intellectual property protection, whereas existing methods face a severe vulnerability against regeneration-based AIGC attacks. We identify that existing methods fail because they entangle the watermark with high-frequency cover texture, which...
Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
arXiv:2602.21550v1 Announce Type: new Abstract: Gene expression prediction, which predicts mRNA expression levels from DNA sequences, presents significant challenges. Previous works often focus on extending input sequence length to locate distal enhancers, which may influence target genes from hundreds of...
The Beginnings Of The One Big Beautiful Bill Act: Placing The 2017 Tax Cuts And Jobs Act In Historical Perspective
On July 4, 2025, President Donald J. Trump signed into law the One Big Beautiful Bill Act (OBBBA). This new law was built on the foundations of its immediate predecessor,the 2017 Tax Cuts and Jobs Act (TCJA). This Essay examines...
Mistral AI inks a deal with global consulting giant Accenture
Mistral AI lands a partnership with Accenture, the consultant that has also recently announced partnerships with rivals OpenAI and Anthropic.
CAMEL: Confidence-Gated Reflection for Reward Modeling
arXiv:2602.20670v1 Announce Type: new Abstract: Reward models play a fundamental role in aligning large language models with human preferences. Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and generative judging models, which...
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
arXiv:2602.20816v1 Announce Type: new Abstract: The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distributions. Traditional KL divergence tends to be dominated by the next tokens with the highest...
Blackbird Language Matrices: A Framework to Investigate the Linguistic Competence of Language Models
arXiv:2602.20966v1 Announce Type: new Abstract: This article describes a novel language task, the Blackbird Language Matrices (BLM) task, inspired by intelligence tests, and illustrates the BLM datasets, their construction and benchmarking, and targeted experiments on chunking and systematicity. BLMs are...
Evaluating Proactive Risk Awareness of Large Language Models
arXiv:2602.20976v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward anticipating unintended but consequential risks. In this work, we introduce a proactive risk...
Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning
arXiv:2602.21103v1 Announce Type: new Abstract: Advanced reasoning typically requires Chain-of-Thought prompting, which is accurate but incurs prohibitive latency and substantial test-time inference costs. The standard alternative, fine-tuning smaller models, often sacrifices interpretability while introducing significant resource and operational overhead. To...
On Data Engineering for Scaling LLM Terminal Capabilities
arXiv:2602.21193v1 Announce Type: new Abstract: Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this gap through a systematic study of data engineering practices...
MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation
arXiv:2602.20423v1 Announce Type: cross Abstract: Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential for dense, text-guided medical image segmentation...
GATES: Self-Distillation under Privileged Context with Consensus Gating
arXiv:2602.20574v1 Announce Type: cross Abstract: We study self-distillation in settings where supervision is unreliable: there are no ground truth labels, verifiable rewards, or external graders to evaluate answers. We focus on document-grounded question answering with asymmetric context, where a single...
Multimodal MRI Report Findings Supervised Brain Lesion Segmentation with Substructures
arXiv:2602.20994v1 Announce Type: cross Abstract: Report-supervised (RSuper) learning seeks to alleviate the need for dense tumor voxel labels with constraints derived from radiology reports (e.g., volumes, counts, sizes, locations). In MRI studies of brain tumors, however, we often involve multi-parametric...
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
arXiv:2602.20207v1 Announce Type: new Abstract: Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages:...
MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
arXiv:2602.20223v1 Announce Type: new Abstract: Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting...
Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning
arXiv:2602.20271v1 Announce Type: new Abstract: Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing complexity of logistics networks, spanning multimodal transportation, cross-country routing, and pronounced regional variability, makes this...
CaDrift: A Time-dependent Causal Generator of Drifting Data Streams
arXiv:2602.20329v1 Announce Type: new Abstract: This work presents Causal Drift Generator (CaDrift), a time-dependent synthetic data generator framework based on Structural Causal Models (SCMs). The framework produces a virtually infinite combination of data streams with controlled shift events and time-dependent...
Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction
arXiv:2602.20344v1 Announce Type: new Abstract: Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However,...
Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
arXiv:2602.20400v1 Announce Type: new Abstract: To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using unsupervised training...
Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA
arXiv:2602.20492v1 Announce Type: new Abstract: Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tune a large language model (LLM) by exchanging locally updated parameters with a subset of neighboring devices via...
A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies
arXiv:2602.20527v1 Announce Type: new Abstract: Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) have advanced rapidly in recent years and have been successfully applied to e-learning environments like intelligent tutoring systems (ITSs). Despite great success, the broader application of DRL...
Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition
arXiv:2602.20530v1 Announce Type: new Abstract: Emotion recognition from multi-modal physiological and behavioral signals plays a pivotal role in affective computing, yet most existing models remain constrained to the prediction of singular emotions in controlled laboratory settings. Real-world human emotional experiences,...
Nvidia has another record quarter amid record capex spends
"The demand for tokens in the world has gone completely exponential," Nvidia CEO Jensen Huang said about the company's earnings.
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
arXiv:2602.19049v1 Announce Type: new Abstract: Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping methods offer limited control...
TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes
arXiv:2602.19079v1 Announce Type: new Abstract: Topic modeling extracts latent themes from large text collections, but leading approaches like BERTopic face critical limitations: stochastic instability, loss of lexical precision ("Embedding Blur"), and reliance on a single data perspective. We present TriTopic,...
How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders
arXiv:2602.19115v1 Announce Type: new Abstract: In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work. Although some studies have shown that...
AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG
arXiv:2602.19127v1 Announce Type: new Abstract: With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction, serves as a...
Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
arXiv:2602.19157v1 Announce Type: new Abstract: Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-specific corpora. While SFT can be...
Retrieval Augmented Enhanced Dual Co-Attention Framework for Target Aware Multimodal Bengali Hateful Meme Detection
arXiv:2602.19212v1 Announce Type: new Abstract: Hateful content on social media increasingly appears as multimodal memes that combine images and text to convey harmful narratives. In low-resource languages such as Bengali, automated detection remains challenging due to limited annotated data, class...
Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations
arXiv:2602.19320v1 Announce Type: new Abstract: Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain...