research

QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding

arXiv:2608.05326v1 Announce Type: cross Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work

Research

Quality Diversity for Reliable Data Driven Time-Use Optimization

DGX agent

arXiv:2608.05230v1 Announce Type: cross Abstract: The daily allocation of the finite 24-hour time budget is strongly associated with physical, mental, and cognitive health. While predictive models can

researcharxiv-cs-ai

7 Aug 2026

Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs

arXiv:2608.05660v1 Announce Type: cross Abstract: As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning ha

Reducing belief in conspiracy theories as they unfold using large language models

arXiv:2608.06151v1 Announce Type: cross Abstract: The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues wi

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

arXiv:2608.05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollou

Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution

arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long

Respect Your Zero-Shot Uncertainty: Conservative Calibration for Test-Time-Adapted Vision-Language Models

arXiv:2608.05945v1 Announce Type: new Abstract: Test-time adaptation (TTA) can improve the recognition accuracy of vision-language models under distribution shift, but often degrades calibration, maki

RIG-RoPE: Relation- and Instance-Gated Rotary Positional Encoding with Duration-Aware Temporal Coordinates

arXiv:2608.05154v1 Announce Type: new Abstract: Rotary positional encoding (RoPE) is a core component of modern language models and has been extended to multimodal LLMs through multidimensional varian

RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction

arXiv:2608.06310v1 Announce Type: cross Abstract: Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong

Scaling Categorical Flow Maps

researchapple-ml-research

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved fo

SciQNet: Two-Stage Multimodal Adaptation for Scientific Image Quality Assessment

arXiv:2608.05691v1 Announce Type: new Abstract: Scientific images are essential for communicating experimental observations, quantitative evidence and conceptual knowledge. Unlike natural images, thei

Shape-Aware Oriented Bounding Box (OBB) to Horizontal Bounding Box (HBB) Conversion

arXiv:2608.05858v1 Announce Type: new Abstract: Accurate object detection in aerial and satellite imagery is dependent upon the bounding box representation. This is especially true for spatially orien

Shapes from Examples: Foundations of Shape Learning in Recursive SHACL

arXiv:2607.27934v2 Announce Type: replace Abstract: SHACL shapes enable data graph validation, making automatic shape learning essential for knowledge graph applications. We investigate the well-known

Signal or Spurious Cue? A Randomized Audit of Survey-Country Metadata in LLM Social Inference

arXiv:2608.06085v1 Announce Type: new Abstract: Survey-country metadata can improve an LLM's forecast of an individual response when informative, yet the same cue may redirect the forecast when assign

Sliding Sensors: Configurable Confidence in State Estimation for Continuum Robots

arXiv:2608.05410v1 Announce Type: new Abstract: Continuum robots often operate in uncertain environments, where accurate state estimation is essential for safe interactions. Estimate uncertainty is in

researcharxiv-cs-ro

Small Foundation Models of Human Cognition and Behaviour

arXiv:2608.05224v1 Announce Type: new Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether t

Sparse Mutual Information Graph Averaging for Improving Random Indexing Embeddings

arXiv:2608.05724v1 Announce Type: new Abstract: Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on

Stability of Ranking-dependent Pair-wise Comparison Patterns in the Analytic Hierarchy Process

arXiv:2608.05958v1 Announce Type: new Abstract: The paper addresses several ranking-dependent decision support methods. Ordinal information on compared objects can be used to improve the quality of ex

STAIL: Semantic Text-Anchored Incremental Learning for Medical Imaging via Large Language Models

arXiv:2608.05808v1 Announce Type: new Abstract: Deep learning models applied to medical image analysis suffer from severe catastrophic forgetting when continually adapting to new clinical tasks in dyn

StyleComposer: Training-Free Multi-Reference Style Composition

arXiv:2608.05213v1 Announce Type: new Abstract: The style of a painting is not monolithic: color, texture, and structure may come from different sources. Existing reference-guided methods transfer the

Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Controlled Interventions

arXiv:2608.06174v1 Announce Type: new Abstract: Compositional analysis of frozen vision encoders should determine both what changed and where it changed. Standard factor probes score these axes separa

Surv-IPTB: An Attention-Based Model for Estimating Individual Probability of Treatment Benefit with Survival Data

arXiv:2608.06288v1 Announce Type: new Abstract: This work presents a novel attention-based framework for estimating the Individual Probability of Treatment Benefit (IPTB) in survival analysis contexts

The em-dash em-beds in Congress: A population-level rise in em-dash frequency in U.S. congressional press releases at the dawn of the large-language-model era, 2021-2025

arXiv:2608.05889v1 Announce Type: cross Abstract: Large language models (LLMs) can leave small stylistic traces in text written with their help. The most discussed is the em-dash (U+2014), especially

The ethics of artificial intelligence in the life sciences: Universality, cultural diversity and an architecture of care

arXiv:2608.05436v1 Announce Type: cross Abstract: The life sciences and health research have started to benefit from artificial intelligence, which raises ethical concerns that are real but, we argue,

The interface of intonation and lexical tone: Boundary phenomena in Mandarin varieties

arXiv:2608.05364v1 Announce Type: new Abstract: This chapter explores the intricate interplay between intonation and tone in Mandarin Chinese varieties, focusing on f0, the primary acoustic cue for bo

The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity

arXiv:2608.06283v1 Announce Type: new Abstract: We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and n

Timestep-Conditioned Transformers for Global Weather Forecasting

arXiv:2608.06241v1 Announce Type: new Abstract: Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a f

To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation

arXiv:2608.05879v1 Announce Type: new Abstract: Text-driven 3D generation has advanced rapidly in creating large-scale outdoor environments and detailed indoor scenes, but these domains are usually sy

Topology-Aware Neighborhood Learning for Source-Free Cross-Scene Hyperspectral Image Classification

arXiv:2608.05964v1 Announce Type: new Abstract: Domain adaptation has advanced cross-scene hyperspectral image classification, significantly improving discriminative capability in complex scenarios. H

Training-Free Token-Level Steering for LLM Personalized Co-Writing

arXiv:2608.06069v1 Announce Type: new Abstract: While Large Language Models (LLMs) show great promise for personalization, they often lack specialized domain knowledge. Conventional solutions like fin

Transcutaneous Spinal Cord Stimulation Disrupts Conscious Ankle Proprioception and Produces a More Constrained Locomotor Pattern in Unimpaired Adults

arXiv:2608.05635v1 Announce Type: cross Abstract: Transcutaneous spinal cord stimulation (tSCS) modulates spinal sensorimotor circuits primarily through activation of afferent networks. While prior wo

researcharxiv-cs-ro

TriQua: Reconciling Granularity and Context in Factuality Evaluation

arXiv:2608.05228v1 Announce Type: new Abstract: The 'decompose-then-verify' paradigm for LLM factuality evaluation faces a fundamental trade-off: atomic facts, i.e., one sentence conveying one unit of

Trust-Based Incentive Mechanisms in Semi-Decentralized Federated Learning Systems

arXiv:2602.08290v2 Announce Type: replace-cross Abstract: In federated learning (FL), decentralized model training allows multi-ple participants to collaboratively improve a shared machine learning mo

TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs

arXiv:2608.05616v1 Announce Type: new Abstract: Despite the remarkable progress of large vision language models (LVLMs), object hallucination remains a fundamental challenge that hinders their trustwo

Turing's Frist Imitation Game: Design Concepts and a Human-Approximates-Machine Reading

arXiv:2608.05558v1 Announce Type: cross Abstract: This paper examines Turing's 1948 report, 'Intelligent Machinery', as an important conceptual source for the later imitation games. Its first contribu

Universal Concept Disruption for SAM3 Image Segmentation

arXiv:2608.05983v1 Announce Type: new Abstract: SAM3 extends promptable segmentation from geometry-driven mask prediction to open-vocabulary concept segmentation, where a text-conditioned grounding mo

URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation

arXiv:2608.05671v1 Announce Type: new Abstract: Previous RGB-D semantic segmentation methods commonly employ dual encoders to separately process RGB and depth inputs, followed by dedicated modules for

Velocity- and Regime-Aware Detection of Intraday Options Market Manipulation, with Explainable Attribution

arXiv:2608.05373v1 Announce Type: cross Abstract: Intraday market manipulation is hard to detect because its footprint is brief, buried in millions of quotes, and statistically similar to ordinary vol

Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators

arXiv:2608.06155v1 Announce Type: cross Abstract: Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and ma

Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization

arXiv:2508.11183v2 Announce Type: replace Abstract: Recent video representation methods that rely on fixed-grid, patch-wise tokenization often exhibit limited versatility.Spatially, uniformly allocati

ViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph Completion

arXiv:2608.05833v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to infer missing entities or relations from incomplete graph structures, and has evolved into multimodal knowledge

Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation

arXiv:2608.05648v1 Announce Type: new Abstract: Video identity replacement seeks to transfer the identities of one or more subjects while preserving the motion, expressions, and temporal structure of

Vorch-Omni: Multi-Task Orchestration of Sight and Sound

arXiv:2608.05803v1 Announce Type: new Abstract: Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches

VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation

arXiv:2608.05782v1 Announce Type: new Abstract: Wearable human activity recognition (HAR) is often limited by the scarcity of labeled sensor data, especially in low-resource, class-imbalanced, and sub

Wan-Animate-2: Pushing the Application Boundaries of Character Animation

arXiv:2608.06009v1 Announce Type: new Abstract: Character image animation remains a foundational yet challenging task in computer vision. Existing approaches can be broadly categorized into three para

When Drafts Evolve: Speculative Decoding Meets Online Learning

arXiv:2603.12617v2 Announce Type: replace-cross Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model

Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation

arXiv:2608.05576v1 Announce Type: new Abstract: When a large language model (LLM) writes Harry Potter fanfiction, it reliably produces fundamental elements of the Hogwarts universe, such as recognizab

Why the Third Axis Is Freedom

arXiv:2608.05423v1 Announce Type: cross Abstract: In generative training, a model produces an output and is penalised for its difference from an example. With one output per comparison, a model that p