Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training
arXiv:2609.19242v1 Announce Type: new
Abstract: Block diffusion language models (BDLMs) combine autoregressive dependencies across blocks with parallel denoising within blocks, but long-context training is constrained by distributed attention communication and activation memory. Conventional contex...
Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices
arXiv:2609.19243v1 Announce Type: new
Abstract: Spectral co-clustering is a useful tool for discovering latent structure in word-document matrices, but its reliance on singular value decomposition (SVD) can make standard formulations expensive on high-dimensional data. This paper presents two rando...
arXiv:2609.19279v1 Announce Type: new
Abstract: Running artificial intelligence (AI) models directly on edge devices such as smartphones, wearables, and drones offers low latency, pervasive scalability, and data privacy, but these devices rarely carry the computing capability that modern neural net...
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
arXiv:2609.19180v1 Announce Type: new
Abstract: Language models face unique challenges in analyzing interdisciplinary scientific research literature. In biophysics research, faithful answers require grounding observed data in source evidence, interpreting it through a quantitative physics model, an...
What Do We Expect from LLMs? Mapping the Design of LLM Benchmarks
arXiv:2609.19182v1 Announce Type: new
Abstract: Benchmarks are central to how progress in large language models (LLMs) is assessed and communicated. Yet model rankings alone reveal little about how evaluation requirements themselves are changing. The expanding variety of benchmarks offers another p...
Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
arXiv:2609.19203v1 Announce Type: new
Abstract: AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as protocols (e.g., MCP, A2A) ease tool/agent connectivity, each framework embeds an implicit runtime f...
Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introd...
Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds
arXiv:2609.17560v1 Announce Type: new
Abstract: Every production model is updated, by retraining, fine-tuning, quantization, or a silent vendor swap, and each update risks being worse than what it replaced. We formalize update promotion as certified paired risk-difference auditing. Our starting poi...
Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs
arXiv:2609.17564v1 Announce Type: new
Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compression Paradox: neural prompt compression can add key-value (KV) cache contention and preprocessing l...
Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives
arXiv:2609.17572v1 Announce Type: new
Abstract: Auditing vision-language models (VLMs) for societal bias requires distinguishing direct algorithmic valuation disparities from confounders embedded within archival metadata. In this study, we audit Contrastive Language-Image Pretraining (CLIP) models ...
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
arXiv:2609.17632v1 Announce Type: new
Abstract: Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment. This limits their ability to adapt how ...
Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
arXiv:2609.17635v1 Announce Type: new
Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the incoming stream as ground truth. We study what happens when it is not. We formalise stealthy false da...
What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization
arXiv:2609.17637v1 Announce Type: new
Abstract: Restricting what a module can read may improve what a system learns to compute. We test this in a preregistered confirmation with sixty four-cell systems sharing a frozen language-model backbone and communicating through learned continuous packets. Fi...
REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff
A central goal of autonomous reinforcement learning is continuous policy training without external resets. However, existing paradigms largely depend on underlying environmental reversibility, a property absent in real world manipulation, where events such as pushing objects off tables or spilling g...
Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents
arXiv:2609.16056v1 Announce Type: new
Abstract: Humans carry behaviour knowledge of how to act in familiar situations into every new task rather than relearning it from scratch. There is no reason a Reinforcement Learning (RL) agent shouldn't do the same: known behaviour patterns need not be learne...
OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
arXiv:2609.16057v1 Announce Type: new
Abstract: Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited generalizability. (2) Reflection is o...
HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning
arXiv:2609.16060v1 Announce Type: new
Abstract: Users often need ask questions and seek answers online. The Question - Answering (QA) forums such as Stack Overflow cannot always respond to the questions timely and properly. In this paper, we propose HintMiner, a novel automatic question hints minin...
Optimal Pruning for Neural Architectures using Fisher Information Distances
arXiv:2609.16129v1 Announce Type: new
Abstract: A new scheme for parameter pruning is introduced, derived from the differential-geometric distance in model space. Pruning a parameter sets its value to zero, representing a displacement of the model to the hypersurface on which that parameter vanishe...
Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation
arXiv:2609.16145v1 Announce Type: new
Abstract: We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? We propose CRN v2, a lightweight logit-level correction module (~34M trainable parameters, 0.73% of t...
GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events
arXiv:2609.16163v1 Announce Type: new
Abstract: The sharp increase in mass shootings underscores an urgent need for systems that guide victims to safety in real time. An effective evacuation system must minimize threat exposure while also accounting for adversarial uncertainty and crowding dynamics...
arXiv:2609.16189v1 Announce Type: new
Abstract: Open-ended strategic wargames are high-stakes LM-based social simulations: they model adversaries, institutions, escalation, plan brittleness, doctrine, and crisis response. Language models (LMs) are attractive because they can play agents, generate s...
Shared Selective Persistent Memory for Agentic LLM Systems
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conver...
Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs
Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt undermines data discovery, access control, and regulatory compliance. We present Glyph, a production s...