arXiv Machine Learning
Aug 11
Regret of exploratory policy improvement and $q$-learning
arXiv:2411. 01302v2 Announce Type: replace Abstract: We study the convergence of $q$-learning and related algorithms introduced by Jia and Zhou (J.
Reinforcement learning
Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv AI
Aug 11
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy
arXiv:2605. 12991v3 Announce Type: replace-cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy.
arXiv AI
Aug 11
Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks
arXiv:2603. 00077v3 Announce Type: replace-cross Abstract: Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduced to exact programmatic checks.
arXiv Machine Learning
Aug 11
From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering
arXiv:2604. 01476v2 Announce Type: replace Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task.
arXiv Machine Learning
Aug 11
Satellite Trajectory Optimization via Proximal Policy Optimization for Space Debris Avoidance
arXiv:2608. 09628v1 Announce Type: new Abstract: Collision avoidance systems are commonly used to avoid fragmentation events occurring in Low-Earth Orbit (LEO) and Geosynchronous Equatorial Orbit (GEO).
arXiv AI
Aug 11
IndexTTS 2.5 Technical Report
arXiv:2601. 03888v4 Announce Type: replace-cross Abstract: In prior work, we introduced IndexTTS 2, a zero-shot neural text-to-speech foundation model comprising two core components: a transformer-based Text-to-Semantic (T2S) module and a non-autoregressive Semantic-to-Mel (S2M) module, which together enable faithful emotion replication and establish the first autoregressive duration-controllable generative paradigm.
arXiv AI
Aug 11
Critic-Free Deep Reinforcement Learning for Maritime Coverage Path Planning on Irregular Hexagonal Grids
arXiv:2603. 28385v2 Announce Type: replace-cross Abstract: Maritime surveillance missions, such as search and rescue and environmental monitoring, rely on the efficient allocation of sensing assets over vast and geometrically complex areas.
arXiv AI
Aug 11
SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning
arXiv:2608. 09138v1 Announce Type: cross Abstract: While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution speeds.
arXiv Machine Learning
Aug 11
Regret, equilibrium, and learning in games: A guided tour
arXiv:2608. 09389v1 Announce Type: cross Abstract: This note aims to serve as an entry point to the literature on learning in games, a topic with significant theoretical appeal and a wide range of applications -- from machine learning and data science to economics and beyond.
arXiv Machine Learning
Aug 11
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
arXiv:2608. 09209v1 Announce Type: cross Abstract: Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs.
arXiv Machine Learning
Aug 11
Multi-Agent Reinforcement Learning via Agent-Specific Preference
arXiv:2608. 08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions.
arXiv Machine Learning
Aug 11
Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training
arXiv:2608. 08224v1 Announce Type: new Abstract: Reinforcement learning post-training unlocks complex reasoning in LLMs.
arXiv Machine Learning
Aug 11
The Sample Complexity of Policy Learning with Mu-Resets
arXiv:2608. 07772v1 Announce Type: new Abstract: We study policy-based reinforcement learning under the $\mu$-resets interaction protocol of Kakade and Langford [KL02].
arXiv AI
Aug 11
Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models
arXiv:2608. 08010v1 Announce Type: cross Abstract: Time series forecasting (TSF) plays an important role in a wide range of real-world applications.
Hugging Face Trending Papers
Aug 10
CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation
Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation alone. Hardware verification is an important application of code generation and accounts for a substantial fraction of modern chip design effort, with high-coverage testbench stimulus generation as a key task.
Hugging Face Trending Papers
Aug 10
DSLE: A Learning Environment for Dark Souls Boss Encounters
We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game-playing agent benchmarks through a Gymnasium-style interface. DSLE combines real-time combat, high-dimensional visual input, and sparse terminal rewards, with each environment step being a real action executed against the running game.
Hugging Face Trending Papers
Aug 10
Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63. 0-68.
Hugging Face Trending Papers
Aug 10
DUET: A Diversity-Quality Duet of Distillation Experts for Two-Step Video Generation
Diffusion models have enabled high-quality video generation in recent years, but the high cost of iterative sampling hinders their practical deployment. Few-step distillation alleviates this cost, yet exposes a quality--diversity trade-off between its two dominant paradigms: trajectory-level distillation (e.
Hugging Face Trending Papers
Aug 10
RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation
Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable flight actions in complex environments. Although recent end-to-end UAV vision-language-action (UAV-VLA) policies reduce reliance on separately designed perception, planning, and control modules, their behavior-cloning objectives provide limited corrective supervision for interactive closed-loop execution.
Hugging Face Trending Papers
Aug 10
Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models
Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources.