arXiv AI
Aug 5
The Transformer Revolution, Part 1: Dynamic Processing through Output- Weight Interconnections
arXiv:2608. 03921v1 Announce Type: new Abstract: This paper offers a new interpretation of the Transformer during inference.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Aug 5
PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement
arXiv:2511. 13300v1 Announce Type: cross Abstract: Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches.
arXiv AI
Aug 5
$S^3$: Improving Agent Safety through Multi-Stage Defense
arXiv:2608. 02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks.
arXiv AI
Aug 5
A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation
arXiv:2608. 02805v1 Announce Type: cross Abstract: In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-form findings from the reports.
arXiv AI
Aug 5
BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?
arXiv:2608. 02867v1 Announce Type: cross Abstract: Although reinforcement learning with verifiable rewards (RLVR) has improved the performance of large language models (LLMs) across a variety of reasoning tasks, there is significant debate as to whether RLVR expands the reasoning capability boundary, or just improves sampling efficiency.
arXiv AI
Aug 5
Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks
arXiv:2608. 03794v1 Announce Type: cross Abstract: Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs).
arXiv AI
Aug 5
GENESIS: Towards Explainable Causal Discovery
arXiv:2608. 03868v1 Announce Type: cross Abstract: Causal Discovery (CD) from observational data faces two fundamental challenges.
arXiv AI
Aug 5
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
arXiv:2602. 13769v3 Announce Type: replace Abstract: Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms.
arXiv AI
Aug 5
LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics
arXiv:2603. 24929v2 Announce Type: replace Abstract: Understanding and quantifying uncertainty in large language model (LLM) outputs is critical for reliable deployment.
arXiv AI
Aug 5
Evaluating LLM-Based Goal Extraction in Requirements Engineering: Prompting Strategies and Their Limitations
arXiv:2604. 22207v2 Announce Type: replace-cross Abstract: Due to the textual and repetitive nature of many Requirements Engineering (RE) artefacts, Large Language Models (LLMs) have proven useful to automate their generation and processing.
arXiv Machine Learning
Aug 5
BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems
arXiv:2608. 02612v1 Announce Type: cross Abstract: Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise.
arXiv AI
Aug 5
ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels
arXiv:2608. 03507v1 Announce Type: cross Abstract: Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages.
arXiv AI
Aug 5
When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary
arXiv:2608. 01679v2 Announce Type: replace Abstract: Persistent memory allows (self-evolving) LLM agents to adapt across tasks by consolidating heterogeneous interaction histories into reusable facts, preferences, observations, and rules.
arXiv AI
Aug 5
Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving
arXiv:2608. 03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters.
arXiv AI
Aug 5
Enhancing Tabular Learners with Context-Aware Semantic Embeddings
arXiv:2608. 03565v1 Announce Type: new Abstract: While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries.
arXiv AI
Aug 5
Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures
arXiv:2608. 02645v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on external tools to perform multistage tasks.
arXiv Machine Learning
Aug 5
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads
arXiv:2608. 02703v1 Announce Type: cross Abstract: Weight-only quantization substantially reduces the storage of large language model (LLM) transformer blocks, but practical backends often retain the final language-modeling head (LM-head) in BF16 or FP16.
arXiv AI
Aug 5
Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning
arXiv:2608. 03028v1 Announce Type: new Abstract: Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision.
arXiv AI
Aug 5
Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational Reasoning
arXiv:2608. 03161v1 Announce Type: new Abstract: Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not fully preserve.
arXiv AI
Aug 5
Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory
arXiv:2608. 03420v1 Announce Type: new Abstract: Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood.