127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

127,664 results

Research

Can SGD Handle Heavy-Tailed Noise?

DGX agent

arXiv:2508.04860v2 Announce Type: replace-cross Abstract: Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- commo

researcharxiv-cs-lg

5 Oct 2026

Research

Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality

DGX agent

arXiv:2603.13725v2 Announce Type: replace Abstract: Memristor-based analog compute-in-memory (CIM) architectures provide a promising substrate for the efficient deployment of Large Language Models (LL

All entries

Can SGD Handle Heavy-Tailed Noise?

Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality

Capability Scaling-Down Laws for LLM Compression

Capturing Dynamics: The 4D Facial Expression Intensity Dataset

Causal discovery identifies pathways linking physical activity to dementia risk in the UK BioBank

Causal Representation Learning with Instantaneous and Lagged Relations via Nonstationarity

Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

Characterizing the Performance Gap in Human Activity Recognition for Older Adults

CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation

Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents

ChromaGS: Text-Driven Semantic Editing of 4D Gaussian Avatars

ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs

ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation

CLEAN: Psychometrically Consistent Incremental Cognitive Diagnosis under Concept-Space Expansion via Architectural Isolation

CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation

Clinical Concept Centers in LLMs

Clockwork.io bags $31M in funding to keep AI inference and training workloads running like … clockwork

Closing the Train-Test Gap in World Models for Gradient-Based Planning

Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization

Coco: An Agentic Copilot for the Hardware--Software Co-Design Lifecycle

Cocoon: A System Architecture for Differentially Private Training with Correlated Noises

Cohere unveils North 2 AI agent platform with rebuilt orchestration and token spending caps

Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents

Collective Bias Mitigation via Model Routing and Collaboration

CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification

CoMemNet: A Continual Memory Network with Drift-Aware Sampling for Traffic Prediction

Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents

Conditional Capacity and Routing in Mixture-of-Experts Particle Transformers

Confidence-Controlled XAI Auditing for Pedestrian Detection under Domain Shift

Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging

Conformal Prediction for Time Series with Deep Sequence Models

Congrats to the Reflection team on Beam 🎉 Be sure to join us next week at our NYC meet-up with the Reflection team and NVIDIA https://luma.…

Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures

Constraint-Aware Training

Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs

Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation

Continual Graph Memory for Mathematical Research Agents

CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role

Controllable Accent Normalization via Discrete Diffusion

Controlling Polar Exposure to Delay Memorization in Diffusion Models

ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution

Cordial Learning: Distributed Training with Correlated Data

CORE: COverage CAlibration and Evicted-Mass REdistribution for KV Cache

CORNAV: Construction-Aware Reasoning for Robot Navigation on Active Worksites

Correcting Guided Diffusion Trajectories with Spectral Alignment

Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally