Search: “models”

More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations

arXiv:2605.26647v1 Announce Type: cross Abstract: Feedforward network (FFN) layers account for a large fraction of parameters and nonlinear expressivity in Transformer-based large language models (LLM

Research

MSCGC-KAN: Multi-scale Causal Graph Convolution and Kolmogorov-Arnold Feature Mapping for EEG Emotion Recognition

DGX agent

arXiv:2605.26624v1 Announce Type: new Abstract: Electroencephalogram (EEG)-based emotion recognition is an important affective computing task, and recent EEG foundation models provide useful generic r

researcharxiv-cs-cv

27 May 2026

NestedKV: Nested Memory Routing for Long-Context KV Cache Compression

arXiv:2605.26678v1 Announce Type: new Abstract: Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank

O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding

model-releasesarxiv-cs-cv

arXiv:2605.26584v1 Announce Type: new Abstract: Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks

Local Ai

OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following

arXiv:2605.26399v1 Announce Type: new Abstract: Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typ

local-aiarxiv-cs-cv

Tutorials

Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics

arXiv:2605.26840v1 Announce Type: new Abstract: Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as

tutorialsarxiv-cs-cl

PaTAS: A Framework for Trust Propagation in Neural Networks Using Subjective Logic

arXiv:2511.20586v4 Announce Type: replace Abstract: Trustworthiness has become a key requirement for the deployment of artificial intelligence systems in safety-critical applications. Conventional eva

Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History

arXiv:2602.17003v2 Announce Type: replace-cross Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail

Position: AI Safety Requires Effective Controllability

arXiv:2605.27117v1 Announce Type: new Abstract: AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing ha

Agents

Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction

arXiv:2602.00959v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far t

agentsarxiv-cs-cl

SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs

arXiv:2512.04868v2 Announce Type: replace-cross Abstract: Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual depend

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens

arXiv:2508.05305v2 Announce Type: replace Abstract: The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-s

Strategies for Guiding LLMs to Use Software Design Patterns: A Case of Singleton

arXiv:2605.26898v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level arc

Structured Relational Reasoning for Group Activity Assessment

model-releasesarxiv-cs-cv

arXiv:2508.07996v2 Announce Type: replace Abstract: Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DI

TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents

arXiv:2601.05899v2 Announce Type: replace Abstract: Recent breakthroughs in Large Language Models (LLMs) have positioned them as a promising paradigm for agents, with long-term planning and decision-m

What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation

arXiv:2605.26795v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly und

WINDQuant: Weight-Informed Neural Decision-Making for Global Mixed-Precision LLM Quantization

arXiv:2605.26660v1 Announce Type: new Abstract: Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in

Acting on the Unseen: Communication-Free Collaborative Filtering for Decentralized Multi-Robot Task Allocation

arXiv:2605.25584v1 Announce Type: cross Abstract: Multi-robot task allocation usually assumes some combination of communication, known task models, or a coordinator. We study the opposite extreme, a r

AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue

arXiv:2605.23974v1 Announce Type: new Abstract: Current language models create two safety challenges: risk must be detected early enough to avoid exposing harmful continuation, and the harmfulness its

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions

arXiv:2605.25707v1 Announce Type: new Abstract: Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digita

An Interactive Paradigm for Deep Research

arXiv:2605.24266v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended q

BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning

arXiv:2511.12046v2 Announce Type: replace-cross Abstract: Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained 'teacher' models downloaded from third-party

researcharxiv-cs-ai

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows

arXiv:2605.24219v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that reason, use tools, and act over multiple steps. Yet most hallucination

Can LoRA Fusion Support Cross-Domain Tasks in Cloud-Edge Collaboration?

arXiv:2605.23913v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) commonly rely on LoRA for domain adaptation, yet domain data are distributed across multiple edge devices an

Chain-of-Thought Hijacking

arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reas

ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale

arXiv:2605.24305v1 Announce Type: cross Abstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Y

Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs

arXiv:2604.18179v2 Announce Type: replace-cross Abstract: Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return scheme

Context-Instrumental Data Distillation for Kubernetes Manifest Generation: Method and Experimental Evaluation

arXiv:2605.25835v1 Announce Type: cross Abstract: This paper examines the specialization of Small Language Models (SLMs) with up to 4 billion parameters for generating artifacts in domain-specific lan

Continual Speaker Identity Unlearning with Minimal Interference

arXiv:2605.25962v1 Announce Type: cross Abstract: Machine unlearning removes designated concepts or knowledge from pre-trained models. Recent work has extended this paradigm to speaker identity unlear

Counterfactual Explanations for Hypergraph Neural Networks

arXiv:2602.04360v2 Announce Type: replace-cross Abstract: Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, l

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

arXiv:2605.25603v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully

researcharxiv-cs-ai

E = T*H/(O+B): A Dimensionless Control Parameter for Mixture-of-Experts Ecology

arXiv:2605.06415v2 Announce Type: replace-cross Abstract: We introduce E = T*H/(O+B), a dimensionless control parameter that predicts whether Mixture-of-Experts (MoE) models will develop a healthy exp

Local Ai

ExplainReduce: Generating global explanations from many local explanations

arXiv:2502.10311v3 Announce Type: replace-cross Abstract: Most commonly used non-linear machine learning methods are closed-box models, uninterpretable to humans. The field of explainable artificial i

local-aiarxiv-cs-ai

Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines

arXiv:2605.25645v1 Announce Type: cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison

Fine-Tuning Masked Diffusion for Provable Self-Correction

arXiv:2510.01384v4 Announce Type: replace Abstract: A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Model

researcharxiv-cs-lg

Forgettable Federated Linear Learning with Certified Data Unlearning

arXiv:2306.02216v3 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative model training across distributed clients while preserving user privacy. Recently, Federated Unlearnin

researcharxiv-cs-lg

From One-Pass SGD to Data Reuse: Mini-Batch Scaling Laws in Sketched Linear Regression

arXiv:2605.24316v1 Announce Type: new Abstract: Scaling laws provide compact descriptions of how prediction error varies with compute, model size, and data, but existing theory mainly treats single-sa

GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration

arXiv:2605.24636v1 Announce Type: new Abstract: While large language models (LLMs) hold transformative potential for medicine, their reasoning robustness and safety in real-world clinical scenarios re

Grammatically-Guided Sparse Attention for Efficient and Interpretable Transformers

arXiv:2605.24518v1 Announce Type: cross Abstract: The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large la

How does Bayesian Sampling help Membership Inference Attacks?

arXiv:2503.07482v2 Announce Type: replace-cross Abstract: Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. Existing state-of

researcharxiv-cs-ai

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference

arXiv:2605.25475v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows line

Agents

Inference-Time Backdoors via Chat Templates: From LLM Supply Chains to Agentic System Compromise

arXiv:2602.04653v4 Announce Type: replace-cross Abstract: Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor at

agentsarxiv-cs-lg

Inference Time Optimization with Confidence Dynamics

arXiv:2605.25244v1 Announce Type: new Abstract: Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs

LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers

arXiv:2605.25415v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adve

LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots

arXiv:2605.24417v1 Announce Type: new Abstract: Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data

MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration

arXiv:2605.25030v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems offer a promising approach to reduce hallucinations and improve answer accuracy in large language models (L

Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent

arXiv:2605.25590v1 Announce Type: cross Abstract: We study nonstationary generalized linear bandits (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-