arXiv AI
6d ago
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
arXiv:2608. 13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.
Natural language processing
Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.
arXiv AI
6d ago
Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
arXiv:2505. 12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets.
arXiv Machine Learning
6d ago
Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models
arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.
arXiv Machine Learning
6d ago
Exemplar-based objective classification of gust-induced loads across multiple flight conditions
arXiv:2608. 12448v1 Announce Type: new Abstract: Is it possible to find an objective classification criterion that organizes the complexity of gust-induced loads across many flight conditions?
arXiv Machine Learning
6d ago
ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization
arXiv:2608. 12756v1 Announce Type: cross Abstract: Adaptive latent tokenization maps a fine-grained input to a shorter sequence of continuous representations associated with input-dependent spans.
arXiv AI
6d ago
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
arXiv:2608. 13160v1 Announce Type: cross Abstract: Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question answering.
arXiv AI
6d ago
Into the ORBIT for Time Series: Training Regimes for Foundation Models
arXiv:2608. 13262v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored.
arXiv AI
6d ago
DiffGRM: Diffusion-based Generative Recommendation Model
arXiv:2510. 21805v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history.
arXiv AI
6d ago
Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement
arXiv:2608. 13129v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including magnitude comparison, large-integer arithmetic, fractions, and scientific notation.
arXiv AI
6d ago
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
arXiv:2608. 13430v1 Announce Type: cross Abstract: Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence.
Hugging Face Trending Papers
6d ago
V-RAE: Rethinking Video Latent Spaces for Generation
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization.
Hugging Face Trending Papers
6d ago
Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces
Medical foundation models learn latent representations of clinically meaningful phenotypes, yet their ability to support controllable image generation remains largely unexplored. We evaluate four retinal foundation models within the representation tokenizer framework and examine whether demographic and clinical information encoded in latent representations from foundation models is preserved during synthetic image generation.
Hugging Face Trending Papers
6d ago
Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?
Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point.
Hugging Face Trending Papers
6d ago
Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement
Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including magnitude comparison, large-integer arithmetic, fractions, and scientific notation. This survey examines basic numerical understanding as a capability distinct from high-level mathematical reasoning.
Hugging Face Trending Papers
6d ago
HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQA
Knowledge-base question answering (KBQA) systems rely on effective retrieval and reasoning mechanisms to generate accurate answers from external knowledge sources. However, developing reliable KBQA systems for low-resource languages such as Bangla remains challenging due to limited retrieval-focused research, scarce language resources, and difficulties in grounding generated responses in external knowledge.
arXiv AI
Aug 13
The Sleeping Agent: What Gist-Based Context Compression Loses and Why
arXiv:2608. 11775v1 Announce Type: new Abstract: Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood.
arXiv AI
Aug 13
AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
arXiv:2608. 11392v1 Announce Type: cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary.
arXiv AI
Aug 13
Dual-Model Sentiment Analysis of Consumer Reviews in the Retail Coffee Sector Using Machine Learning and Deep Learning Approaches
arXiv:2608. 12007v1 Announce Type: cross Abstract: Consumer reviews play an important role in shaping brand perception and business strategies, particularly in service-driven industries such as retail coffee.
arXiv AI
Aug 13
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
arXiv:2608. 12262v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration.
arXiv Machine Learning
Aug 13
Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms
arXiv:2505. 23696v2 Announce Type: replace Abstract: Solving systems of polynomial equations, particularly those with finitely many solutions, is a crucial challenge across many scientific fields.