arXiv AI
Jul 28
Embodied GPT-5.1: Evidence of a World Model?
arXiv:2607. 23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 28
DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training
arXiv:2607. 22614v1 Announce Type: new Abstract: RL-based LLM post-training increasingly disaggregates Rollout and Training across separate GPU resources, but static GPU partitioning suffers from severe pipeline bubbles under long-tail rollout latency.
arXiv AI
Jul 28
Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety Architecture
arXiv:2607. 22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk.
arXiv AI
Jul 28
Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations
arXiv:2607. 22610v1 Announce Type: new Abstract: When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turns?
arXiv AI
Jul 28
HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering
arXiv:2607. 22597v1 Announce Type: new Abstract: Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process.
arXiv AI
Jul 28
TriSP: Tri-Signal Structured Pruning for Large Language Models
arXiv:2607. 22587v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters.
arXiv AI
Jul 28
Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning
arXiv:2607. 23605v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) now act as agents in interactive environments, where success requires coherent reasoning and decision-making across turns.
arXiv AI
Jul 28
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
arXiv:2607. 23802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has driven recent progress in reasoning-oriented large language models (LLMs) by enabling large-scale optimization.
arXiv AI
Jul 28
E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios
arXiv:2607. 23722v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden information, composing tool calls, and committing state changes.
arXiv AI
Jul 28
Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias
arXiv:2607. 22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns around sensitive data.
arXiv AI
Jul 28
Kalypso: Relational LLM Serving
arXiv:2607. 23815v1 Announce Type: cross Abstract: Large language models are increasingly used as semantic operators for filtering, extracting, ranking, joining, and transforming unstructured data.
arXiv AI
Jul 28
The Half-Lives of Generative-AI Evidence: A 40-Record Audit, a Claim-Currency Framework, and a Reflexive Case of Frontier-Model-Assisted Research
arXiv:2607. 24032v1 Announce Type: new Abstract: Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally.
arXiv AI
Jul 28
MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models
arXiv:2607. 22566v1 Announce Type: new Abstract: MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue.
arXiv AI
Jul 28
SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding
arXiv:2607. 23991v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly controlled through system prompts that specify roles, styles, formats, and safety requirements.
arXiv AI
Jul 28
Reference Feature Atlases for Mechanistic Auditing of Language Models
arXiv:2607. 22570v1 Announce Type: new Abstract: Auditing a new language model usually means relearning and reinterpreting its internal features from scratch.
arXiv AI
Jul 28
HELIOS: An LLM-Driven Autonomous Indirect Trajectory Optimization Agent
arXiv:2607. 24051v1 Announce Type: cross Abstract: Low-thrust trajectory optimization is a core technology in deep-space mission design.
arXiv AI
Jul 28
Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning
arXiv:2607. 22697v1 Announce Type: new Abstract: Deployed AI systems are often trained from broad candidate data pools, necessitating data curation towards the deployment test distribution.
arXiv Machine Learning
Jul 28
Visual Token Compression Enhances Robustness of MLLMs
arXiv:2607. 22716v1 Announce Type: cross Abstract: In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations.
arXiv Machine Learning
Jul 28
Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions
arXiv:2506. 05678v3 Announce Type: replace Abstract: The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in sequential data.
arXiv AI
Jul 28
Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting
arXiv:2602. 17634v2 Announce Type: replace-cross Abstract: Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains.