127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “models”

95,172 results

Syntheses

Synthesis: Arxiv-Cs-Ai

DGX agent

Auto-generated synthesis of 29846 entries about arxiv-cs-ai

synthesisarxiv-cs-aiauto-generated

4 Oct 2026

Local Ai

Sopro V2 Turbo 2610: cleaner cloned voices, same 120M model, same CPU speed

DGX agent

Follow-up to last month's post. One of the main issues people ran into was roughness or break-up on some cloned voices. 2610 is an interim update focused mostly on improving that. Reduced roughness an

local-ai

Search: “models”

Synthesis: Arxiv-Cs-Ai

Sopro V2 Turbo 2610: cleaner cloned voices, same 120M model, same CPU speed

4 mins plus for a response to simple 'Reply with: Ok'

Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs

CLASP: Continual Low-rank Adapters for Spatially Placed Concepts from One Hypernetwork

EIDA: Execution-Interface Dynamics Adaptation for Real-to-Sim-to-Real Robot Navigation

Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation Tasks

Large Language Bayes Is Not Reparameterisation-Invariant

Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget

Learning to Predict Distributions over Weight Updates for Test-Time Adaptation

Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs

Q-Learning for Reachability in MEC-Free MDPs

Query Independent Variable Rate Visual Token Coding

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Sequential Functional Structured Tucker Compression for Large Language Model Attentions

SLIM: Simplex-Lattice Interpolation Merging

STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation

AMA about K2 Horizon, Meet our team from IFM

AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD

ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning

Asymptotic Properties of Support Vector Machines in High-Dimension, Low-Sample-Size Settings under a Spiked Model

CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL

Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning

CORE: Conflict-Oriented Reasoning Elimination for Verifiable Language-Model Search

Determining Vertical Displacement of Agricultural Areas Using UAV-Photogrammetry and a Heteroscedastic Deep Learning Model

Generative sequence modeling for infinite memory processes via predictive states

GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning

Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs

LocoWM: High-Precision Locomotion through World-Model-Guided Residual Adaptation

Lowest Span Confidence: Zero-Shot Hallucination Detection from a Single LLM Response

MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary

OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimization

OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software

Patient-Centered Treatment Planning for Chronic Multimorbidity: A Hierarchical Reinforcement Learning Framework for Preference Modeling

ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization

SimTrace: Grounded Multimodal User Trajectories Generation for Online User Modeling

Spherical Interpolation for Backward-Compatible Multimodal Representations

The Nixtlaverse: An Open-Source Ecosystem for Forecasting

Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation

Wavelet Flow Matching for Time Series

AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling

CyFA: Linear Sequence Modeling with Relative-Time-Partitioned Memory

Foundation-Model-Guided Topology-Aware Semantic Risk Fields for Manipulation

GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs

GeoSET: Generalist Foundation Model for SAR-to-EO Image Translation