Training & Fine-tuning A

On-Policy and Off-Policy Learning for Large Action Spaces

Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

HARGO: Heterogeneity-Aware Reward-Guided Optimization for RL Post-Training of LLMs on HPC Tasks

Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras

CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance

Agentic Method for Deterministic Validation of Legacy Code Migration

Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory

LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning

Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training

From Expert Reduction to Behavioral Divergence: Tracing Numerical State through Sparse MoE Inference

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios

SemPIC: Learning Semantic Position-Independent KV Caches

A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

Building a User Foundation Model for the Open Web

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

FinanceHarness: Autonomous Financial Deep Research Framework

Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO

Baikal: Structured Search for Deep Research over Data Lakes

Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection

Training Skills Like Parameters via Self-Supervised Semantic Diffusion

Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?

DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search

Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork

Improving Item Discoverability in e-Commerce Search via Related Intent Generation