arXiv AI
Jul 3
Multi-Head Recurrent Memory Agents
arXiv:2607. 01523v1 Announce Type: cross Abstract: Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input into a fixed-size memory window.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jul 3
Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
arXiv:2607. 01710v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging.
arXiv Machine Learning
Jul 3
Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery
arXiv:2607. 01280v1 Announce Type: new Abstract: Programming-by-example systems infer programs from a small set of input-output examples.
arXiv AI
Jul 3
Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
arXiv:2607. 01457v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distinct from general text generation: anachronistic technology injection, cross-domain terminology contamination, structural mutation, and content fabrication.
arXiv Machine Learning
Jul 3
Structured Gaussian Processes for Uncertainty-Aware Classification of High-Dimensional, Small-Sampled Omics Data
arXiv:2607. 02103v1 Announce Type: cross Abstract: Classifying heterogeneous omics data remains a fundamental challenge in computational biology, particularly in high-dimensional, small-sample settings where nonlinear interactions dominate and class imbalance further complicates reliable prediction of minority phenotypes.
arXiv AI
Jul 3
Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification
arXiv:2607. 01272v1 Announce Type: cross Abstract: Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware.
arXiv Machine Learning
Jul 3
I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
arXiv:2607. 01279v1 Announce Type: new Abstract: Cross-subject EEG stress detection remains challenging because discriminative stress-related patterns are both subject-dependent and frequency-specific.
arXiv AI
Jul 3
Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
arXiv:2507. 02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure and training methodologies that are both scalable and sustainable.
arXiv AI
Jul 3
eCream-MedCorpus A Large-Scale Corpus of Clinical Notes for Italian
arXiv:2606. 12569v2 Announce Type: replace-cross Abstract: We present eCream-MedCorpus, a new and unique large-scale dataset of clinical notes produced in Emergency Departments of Italian hospitals.
arXiv AI
Jul 3
Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry
arXiv:2607. 01661v1 Announce Type: new Abstract: Multi-agent systems are increasingly used for forecasting future events, as deliberation among multiple LLMs is believed to improve reasoning and calibration.
arXiv AI
Jul 3
Aria: An Agent For Retrieval and Iterative Auto-Formalization via Dependency Graph
arXiv:2510. 04520v2 Announce Type: replace Abstract: Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their inability to synthesize new definitions.
arXiv AI
Jul 3
Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation
arXiv:2607. 01754v1 Announce Type: new Abstract: On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution.
arXiv Machine Learning
Jul 3
ZENITH: Automated Gradient Norm Informed Stochastic Optimization
arXiv:2601. 15212v2 Announce Type: replace Abstract: Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule.
arXiv AI
Jul 3
Understanding Agent-Based Patching of Compiler Missed Optimizations
arXiv:2607. 02370v1 Announce Type: cross Abstract: Compiler missed optimizations refer to cases in which compilers failed to optimize certain code.
arXiv AI
Jul 3
OmniGAIA: Towards Native Omni-Modal AI Agents
arXiv:2602. 22897v3 Announce Type: replace Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world.
arXiv AI
Jul 3
Working Paper: Towards a Category-theoretic Comparative Framework for Artificial General Intelligence
arXiv:2603. 28906v4 Announce Type: replace Abstract: AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit.
arXiv Machine Learning
Jul 3
Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference
arXiv:2607. 01831v1 Announce Type: cross Abstract: Long-context inference is increasingly common in large language model (LLM) serving, driven by retrieval-augmented generation and agentic systems.
arXiv AI
Jul 3
BRIDGE: Predicting Human Task Completion Time From Model Performance
arXiv:2602. 07267v2 Announce Type: replace Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty.
arXiv Machine Learning
Jul 3
From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection
arXiv:2512. 10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored.
arXiv AI
Jul 3
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
arXiv:2607. 02469v1 Announce Type: cross Abstract: Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior.