![[2605.31289] The Terminal Representation in Reinforcement Learning](/static/img/curated/desks/afbytes-tech.png)
Abstract page for arXiv paper 2605.31289: The Terminal Representation in Reinforcement Learning
Latest in Ai
Abstract page for arXiv paper 2605.31295: Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
Abstract page for arXiv paper 2605.31324: Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
Abstract page for arXiv paper 2605.31330: Social welfare optimisation under institutional reward and punishment
Abstract page for arXiv paper 2605.31340: Appropriateness of Empathy in AI: A Signal-Cost Perspective
Abstract page for arXiv paper 2605.31349: FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
Abstract page for arXiv paper 2605.31360: dashi: A Python library for Dataset Shift Characterization to Support Trustworthy AI Development and Deployment
Abstract page for arXiv paper 2605.31361: Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning
Abstract page for arXiv paper 2605.31251: ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models
Abstract page for arXiv paper 2605.31393: Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
Abstract page for arXiv paper 2605.31404: The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spati...
Abstract page for arXiv paper 2605.31408: Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study
Abstract page for arXiv paper 2605.31421: Neuro-symbolic Syntactic Parsing: Shaping a Neural Network with the CYK Algorithm
Abstract page for arXiv paper 2605.31432: DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
Abstract page for arXiv paper 2605.31445: Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information
Abstract page for arXiv paper 2605.31446: Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction
Abstract page for arXiv paper 2605.31463: PithTrain: A Compact and Agent-Native MoE Training System
Abstract page for arXiv paper 2605.31464: GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
Abstract page for arXiv paper 2605.31469: Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus
Abstract page for arXiv paper 2605.31373: Scaling Higher-Order Graph Learning with Maximal Clique Complexes
Abstract page for arXiv paper 2605.31377: DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval
Abstract page for arXiv paper 2605.31500: On Efficient Scaling of GNNs via IO-Aware Layers Implementations
Abstract page for arXiv paper 2605.31509: Skill Reuse as Compression in Agentic RL
Abstract page for arXiv paper 2605.31514: If LLMs Have Human-Like Attributes, Then So Does Age of Empires II
Abstract page for arXiv paper 2605.31520: Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
Abstract page for arXiv paper 2605.31534: Feature-Optimized Vision for Adaptive 3D Scene Reconstruction
Abstract page for arXiv paper 2605.31535: RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
Abstract page for arXiv paper 2605.31556: Vision-Language Models Suppress Female Representations Under Ambiguous Input
Abstract page for arXiv paper 2605.31558: Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
Abstract page for arXiv paper 2605.31564: What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation
Abstract page for arXiv paper 2605.31575: SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
Abstract page for arXiv paper 2505.17607: Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning
Abstract page for arXiv paper 2507.05488: OLG++: A Semantic Extension of Obligation Logic Graph
Abstract page for arXiv paper 2509.00834: Neuro-Symbolic Predictive Process Monitoring
Abstract page for arXiv paper 2510.02060: ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection
Abstract page for arXiv paper 2510.05115: SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
Abstract page for arXiv paper 2511.04393: Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
Abstract page for arXiv paper 2605.31584: LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Abstract page for arXiv paper 2605.31586: Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus ...
Abstract page for arXiv paper 2605.31590: TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
Abstract page for arXiv paper 2605.31593: Stateful Online Monitoring Catches Distributed Agent Attacks
Abstract page for arXiv paper 2605.31603: Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Abstract page for arXiv paper 2409.14583: LLM Bias Evaluation: Gender, Racial, and Age Disparities in Occupational and Crime Scenarios
Abstract page for arXiv paper 2502.04554: Unifying and Optimizing Data Values for Selection via Sequential Decision-Making
Abstract page for arXiv paper 2502.04671: ProofWala: A Framework for Multilingual Proof Data Synthesis and Theorem-Proving
Abstract page for arXiv paper 2503.08679: Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
Abstract page for arXiv paper 2503.14190: Inferring Events from Time Series using Language Models
New and Enhanced NVIDIA DOCA Security Capabilities for Vera BlueField-4 STX Help Protect AI Agents, Context Memory and File-Based Data Access Directly in Silico...
NVIDIA Vera Rubin Ramps Into Full Production to Power Agentic AI Factories Worldwide
NVIDIA DSX Gives Infrastructure Builders the Playbook for AI Factories