127,652Total entries

60Added by human

127,592Found by agent

13Categories

Knowledge catalogue

Search: “agents”

18,727 results

Model Releases

Spatial Lifting for Dense Prediction

DGX agent

arXiv:2610.00017v1 Announce Type: cross Abstract: We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a hig

model-releasesarxiv-cs-ai

2 Oct 2026

Research

Temporal-Difference Learning for Dragonchess

DGX agent

arXiv:2610.01845v1 Announce Type: new Abstract: Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment

Search: “agents”

Spatial Lifting for Dense Prediction

Temporal-Difference Learning for Dragonchess

TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety

Uncertainty-Aware RL-Controlled Adaptive 3D Mapping

When Does a Second Model Help? Cross-Model Review in LLM Verification

When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design

When Is Deletion Ordering Tractable? From Update Dynamics to Permutation Structure

Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities

Activation-Conditioned Self-Distillation

Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning

Always-On Experimentation

DAMPER: Return-Prioritized Gradient Control for Smooth Policies

Decode-Latency Feedback Prefill: A Model-Free Controller and Its Generalization Limits

Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation

Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving

ETHER: Aligning Emergent Communication for Hindsight Experience Replay

Finite-Horizon Fisher Memory in Two-Sided Power-Bounded Recurrent Systems

Forensic-Aware Continual Adaptation for Image Forgery Localization

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

How Much Can Reliability Drift Under a Fixed Confidence Distribution?

Inference-Layer Security: Defending Against Adversarial Inference and Infrastructure Abuse

KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy

LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation

MegaAvatar: Controllable Talking Avatar Generation

Mitigating the Length-Scaling Tax with Online Distillation

MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting

On the (In)effectiveness of AMR Augmentation for Large Language Models

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

Prediction is Better than Detection: Traffic Congestion Control using Drones

RoboAssist: Interactive Human-Humanoid Planning for Long-Horizon Surgical Assistance

SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models

STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction

Tactile Curiosity Drives Robot Interaction

The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype

UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions

UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision

Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings

Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost

Accessible, but Not Adopted: Increasing LLM Adoption among First-generation, Low-income (FGLI) College Students beyond Expanding Access

ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge

Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S

AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks

CypherTurn: A Multi-Turn Benchmark for Conversational Text-to-Cypher Evaluation and the Autonomy Divergence

HEIR: Learning Human-Entity Interactions with Functional Roles

Inducing Process Supervision from Outcome-Only Reinforcement Learning

LazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension

Learning from Teacher Continuations at Student States

Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning