arXiv AI
Aug 5
On the missing data layer and a potential solution
arXiv:2608. 02949v1 Announce Type: new Abstract: Latin America is missing two foundational layers of AI infrastructure: the dataset layer and the benchmark layer.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Aug 5
Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search
arXiv:2608. 03129v1 Announce Type: new Abstract: Large Language Model-assisted Evolutionary Search (LES) has emerged as a powerful paradigm for automated algorithm design.
arXiv AI
Aug 5
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
arXiv:2608. 03219v1 Announce Type: new Abstract: Benchmark gains are often treated as evidence of greater LLM capability.
arXiv AI
Aug 5
Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition
arXiv:2608. 03892v1 Announce Type: new Abstract: We study linear representations of temporal horizon in the large language model Qwen3-32B and use them to change the model's time-related preferences, recommendations, and capabilities.
arXiv AI
Aug 5
Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation
arXiv:2608. 02639v1 Announce Type: cross Abstract: Production prompts rarely carry a single instruction.
arXiv AI
Aug 5
Training Documents Reranker with Search Rubrics for Deep Research Agent
arXiv:2608. 03527v1 Announce Type: cross Abstract: Retrieval systems help deep research agents generate high-quality answers by providing relevant documents.
arXiv AI
Aug 5
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
arXiv:2602. 01997v3 Announce Type: replace-cross Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks, often with little or no finetuning.
arXiv AI
Aug 5
Cross-Layer Interaction under Weight-Space Ablation: A Closed-Form Attention Jacobian Bound and a Test on a Real Pretrained Model
arXiv:2608. 03629v1 Announce Type: new Abstract: A companion paper studies when activation patching and weight-space ablation agree, inside an idealized model where a conditional computation is carried additively through a residual stream.
arXiv AI
Aug 5
Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking
arXiv:2608. 03859v1 Announce Type: cross Abstract: Large language models (LLMs) pose challenges to academic integrity and peer review.
arXiv AI
Aug 5
Externally Validated Breast Ultrasound Segmentation via Multi-task Learning with BI-RADS-Consistent Morphological Priors
arXiv:2511. 15968v2 Announce Type: replace-cross Abstract: External validation of breast ultrasound segmentation models remains limited because internal train--test splits do not capture domain shifts across imaging systems, acquisition protocols, and patient populations.
arXiv AI
Aug 5
Output-Aware Rotation for INT2 KV-Cache Quantization
arXiv:2608. 02691v1 Announce Type: cross Abstract: The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important.
arXiv Machine Learning
Aug 5
Operationally Feasible Synthetic Power-Grid Scenarios via Learning the AC-Operable Joint Distribution
arXiv:2608. 03878v1 Announce Type: new Abstract: Synthetic power-grid scenarios are essential for planning, resilience assessment, contingency analysis, and data-driven power-system applications.
arXiv AI
Aug 5
Can LLMs Test Terminal User Interfaces?
arXiv:2608. 03743v1 Announce Type: cross Abstract: Terminal User Interfaces (TUIs) combine the stateful, screen-oriented behaviour of GUIs with terminal deployment and are now common in developer tools.
arXiv AI
Aug 5
CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
arXiv:2608. 03890v1 Announce Type: cross Abstract: A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend.
arXiv Machine Learning
Aug 5
Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation
arXiv:2608. 02694v1 Announce Type: cross Abstract: Long-horizon video editing agents receive final-product feedback only after many interdependent decisions.
arXiv Machine Learning
Aug 5
Joint Affine Spectral Shaping: Coupling Weight and Bias Updates Beyond Weight-Only Muon
arXiv:2608. 02991v1 Announce Type: new Abstract: Matrix spectral optimizers reshape weight-update spectra but usually delegate vector-valued biases to a separate optimizer.
arXiv Machine Learning
Aug 5
SAKI: Score-Aware Low-Rank Key Indexing for Long-Context KV Retrieval
arXiv:2608. 03228v1 Announce Type: new Abstract: Existing low rank KV cache methods preserve either model weights or key variance, neither of which directly reflects the attention scores used during inference.
arXiv Machine Learning
Aug 5
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
arXiv:2608. 00155v1 Announce Type: cross Abstract: Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience.
arXiv AI
Aug 5
TumorBoard: Evidence-Grounded Multi-Agent Decision Support for Longitudinal Neuro-Oncology
arXiv:2608. 03190v1 Announce Type: new Abstract: Neuro-oncology decisions require coordinated interpretation of serial MRI, pathology, molecular markers, treatment history, performance status, and evolving guidelines.
arXiv AI
Aug 5
Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities
arXiv:2608. 03569v1 Announce Type: new Abstract: Benchmarking the ability of AI scientists to generate novel ideas is notoriously difficult.