Results for “models”

arXiv (research papers) Josh Rountree SI

Causal Concept Explanations for Deep Neural Models

Concept-based explanations in neural models are important for the development, certification, and adoption of autonomous systems. Yet, interpretability remains correlational. Without methods to guide and quantify causal relationships between explanations, a concept explanation can be provided without being necessary or sufficient for the observed output thereby appearing correct while misleading. We introduce Causal Concept Wrapper Network (CCW-Net), the first use of…

Read at arXiv (research papers)

arXiv (research papers) Amir Mann SI

Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models

Diffusion Language Models (DLMs) have emerged as effective alternatives to autoregressive models for latency-critical tasks, enabling faster token generation. Recent advances employ block diffusion with self-editing capabilities, where each block refines tokens iteratively before advancing to the next one. Yet each block is only as fast as its slowest token, and the next block cannot start before it. We suggest Blurring the Block Boundaries (B3), a novel method with which…

Read at arXiv (research papers)

arXiv (research papers) Bo Dai SI

An Energy-Based Perspective on Machine Learning

Energy-based models (EBMs) define a distribution through a scalar energy, $p_θ(x)\propto\exp(-E_θ(x))$, and are usually presented as one model family among many. This tutorial has a broader goal: beyond introducing EBMs, it uses them as a single lens that connects the different aspects of machine learning. Any EBM is specified by three choices, the energy, which determines what the model represents; the inference procedure, which samples from or optimizes the energy; and the…

Read at arXiv (research papers)

arXiv (research papers) Dong Han SI

Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models

Large language models (LLMs) increasingly exhibit capabilities that resemble human Learning by Thinking (LbT), the acquisition of new insight through internal processes such as explanation and reasoning, without new external input. A systematic account of the cognitive mechanisms behind these capabilities, and of their limits, remains underdeveloped. This paper proposes a Cognitive LbT Framework that maps four mechanisms (Reflective Reasoning, Synthetic Memory Formation…

Read at arXiv (research papers)

arXiv (research papers) Guoqiang Liang

From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models

Pretrained video diffusion models (VDMs) offer a powerful foundation for World Action Models (WAMs), which jointly predict robot actions and future observations. Building such models requires injecting low-dimensional robot signals (e.g. proprioception, actions, and values) into a latent space shaped by natural videos, and a key design choice is the interface through which these signals enter: existing schemes treat it as a formatting detail, spending a separate latent frame…

Read at arXiv (research papers)

arXiv (research papers) Zhengxiang Huang SI

EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities

Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, graph construction, operators, and hardware backends. Existing coding agents often miss these cross-layer dependencies and struggle to diagnose failures across host--device execution paths. We present EngineAgent, an agentic system for automating…

Read at arXiv (research papers)

arXiv (research papers) S M Rayeed SI

CLADE: Category-Level Answering from Deficient Evidence in Retrieval-Augmented Language Models

Retrieval-augmented systems often retrieve passages that are accurate and relevant but state the answer at a coarser level of granularity than the question requires. For example, a question may ask which specific disease a drug treats (familial hyperlipidemia), while the retrieved passage mentions the broader disease family (hyperlipidemia). Prior work on context sufficiency treats such coarse passages simply as insufficient. We argue that they form a distinct case, which we…

Read at arXiv (research papers)

arXiv (research papers) Zihan Chen SI

AI Isn't Getting Dumber, We're Getting Pickier: Rising Standards in Human Evaluation of Large Language Models

Users often complain that AI assistants such as ChatGPT are getting worse. Some versions do change, but human evaluation leaves a second possibility untested: the people judging may change. We separate the two on Chatbot Arena, a public platform where people compare answers from two anonymous large language models (LLMs) and pick the better one or say both are bad. We study 1,260,967 blind votes cast from May 2023 to August 2024 on pairs of models whose versions are fixed…

Read at arXiv (research papers)

Digital Trends DT Staff

iVANKY’s Black Friday Sale Targets Mac Users Who Need More Connectivity

iVANKY's Black Friday sale brings discounts on three FusionDock models, giving Mac users more options for expanding their desktop connectivity. Here's what each dock offers and how much you can save.

Read at Digital Trends

arXiv (research papers) Yuan Zhang Tech policy

Can AI be a 'Researcher Without Borders'? Auditing Bias in AI-Assisted Social Science Research about China and the US

Although large language models have demonstrated strong performance on algorithmic and mathematical tasks, their suitability as social science research assistants remains unclear, particularly because many social science questions lack agreed-upon, quantifiable benchmark answers. Evaluating this suitability is important since researchers and students increasingly rely on AI to generate research ideas. When questions concern the countries in which models were developed, bias…

Read at arXiv (research papers)

arXiv (research papers) Haitian Li

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we…

Read at arXiv (research papers)

arXiv (research papers) Shuting Yang Security

Location Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion Personalization

Text-to-image diffusion models can learn and reproduce an individual's identity from only a few reference photos, creating risks of unauthorized and misleading content generation. Proactive defenses address this risk by adding adversarial perturbations to facial images before release, thereby disrupting identity acquisition during downstream personalization. However, existing methods typically rely on dense $L_\infty$-bounded perturbations, whose accumulated distortions can…

Read at arXiv (research papers)

arXiv (research papers) Mehmet Onur Keskin

Personalized Affective Perception via Continual Learning in Human-Agent Negotiation

Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that incorporates Continual Learning with Imagination for Facial Expression Recognition (CLIFER) to personalize valence-arousal perception in real time. Differential feedback…

Read at arXiv (research papers)

ZDNET AI Nina Raemont SI

Your FitBit Versa and Sense smartwatches will lose some features this month – what to know

Time’s running out for some Versa and Sense models. After Nov. 28, you can no longer install or update third-party apps or clockfaces on these Google smartwatches.

Read at ZDNET AI

The Hacker News Security

Fireworks AI Breach Widens to Expose Customer Billing Data and Incomplete Model Weights

Fireworks AI disclosed on Monday that its investigation into a security incident first reported early last month uncovered further malicious activity, affecting account and billing information, alongside secrets, datasets, and incomplete models for a "limited set of accounts." In a notice published on October 10, 2026, the company said it detected unauthorized use of internal Fireworks

Read at The Hacker News

arXiv (research papers) Yuhong Wang Security

GARD: Gradient-Guided Adversarial Representation Defense against Backdoors in Multimodal Contrastive Learning Models

Multimodal contrastive learning models such as CLIP are vulnerable to backdoor attacks with diverse trigger structures, ranging from localized patches to globally distributed perturbations, with recent attacks increasingly optimizing these triggers in the representation space. Existing post-hoc defenses based on clean fine-tuning may leave backdoors active, while trigger-inversion methods depend on accurately estimating the attack target and trigger. We observe that…

Read at arXiv (research papers)

arXiv (research papers) Qinfeng Zhu

LEASH: Stay Safe in Agentic Robotics

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to control robots poses serious safety risks, and comprehensive safety evaluation is still lacking. We introduce RoboRisk, a comprehensive benchmark for evaluating safety in agentic robotics. Its 92…

Read at arXiv (research papers)

SiliconANGLE AI Duncan Riley SI

KORA builds AI models and agents into a new Linux OS bound for Qualcomm Snapdragon PCs

Desktop software company KORA Systems Inc. today unveiled KORA, a Linux-based operating system that builds artificial intelligence models and agents into the system itself. Qualcomm Technologies Inc. has spent close to a year working with the company to bring it to Snapdragon-powered PCs. The launch goes after what KORA sees as a ceiling on AI

Read at SiliconANGLE AI

WIRED AI Reece Rogers SI

This New Linux-Based Desktop Operating System Is Built for AI Nerds

Built by Cyanogen’s cofounder, Kora is a next-gen alternative to Windows and macOS built for power users running local AI models.

Read at WIRED AI

TechCrunch Startups Jagmeet Singh Startups

After challenging Google’s Android with Cyanogen, its co-founder takes aim at Windows for AI era

Kora is set to launch as a free-to-use alternative to Windows, targeting users who rely heavily on AI models and agents.

Read at TechCrunch Startups

arXiv (research papers) Tomer Solberg Security

Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

We present Sable, an argument system and single-GPU prover for the statement that a committed, integer-quantized transformer produced a given token sequence from a given prompt, bit for bit. Sable fixes an integer function F_O with no floating-point step, in which every rounding, normalization, softmax and sampling decision is determined by its inputs, and proves it with a constraint system whose relations provably never wrap modulo the 31-bit KoalaBear prime. The proof…

Read at arXiv (research papers)

arXiv (research papers) Rezwan Islam Salvi SI

HandsOnAid: Building and Evaluating an Offline First-Aid Assistant for Emergency Response Scenarios

Emergencies can occur where there is no phone signal and no ambulance nearby. A small language model on a phone can be helpful in such situations, but its advice needs to be safe and accurate. We built HandsOnAid, a 4-bit Gemma 2B model fine-tuned with QLoRA on FirstAidQA dataset, a corpus of 5,550 first-aid question-answer pairs. We compared seven configurations, including the base, 4-bit and 8-bit fine-tuned models, and versions with a length floor, safety gate, or…

Read at arXiv (research papers)

arXiv (research papers) Xuheng Zhang

LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning

World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation, endowing policies with strong capabilities for modeling temporal and physical dynamics. Existing WAMs, encompassing both video-first action prediction and joint video-action modeling, directly transfer global physical representations from world models to action generation. However, global scene representations may underemphasize local robot-object interactions, creating a…

Read at arXiv (research papers)

arXiv (research papers) Edward Jiang

Normalizing Flows for Classical Simulation of Quantum Circuits in Phase Space

We present a novel framework to learn a representation of quantum circuits based on the phase space formulation of many-body systems. Given that $N$-qubit states can be represented as probability distributions on a smooth $2N$-dimensional manifold, we show how unitary gates can be parameterized as normalizing flows between these distributions, opening a new avenue for quantum circuit simulation using generative models. We evaluate our method on three common families of…

Read at arXiv (research papers)

arXiv (research papers) Xingqi Wang SI

Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities but raise significant privacy concerns due to their abilities to infer sensitive personal information from images with high precision. While current LVLMs are relatively well aligned to protect universal privacy, e.g., credit card data, we argue that privacy is inherently personalized and context-dependent. This work pivots towards a novel task: can LVLMs achieve Inference-Time Personalized…

Read at arXiv (research papers)

arXiv (research papers) Zhenhong Zhou SI

Understanding Mixture-of-Experts Language Models Beyond Expert Boundaries

In Mixture-of-Experts (MoE) models, the nature of expert specialization remains controversial. Reports of domain-associated expert preferences contrast with analyses attributing routing primarily to token identity or syntactic patterns. To clarify these differing accounts, we look beyond expert-level routing to investigate the neuron-level organization of domain-specialized computation using Routing-Aware Magnitude Profiling (RAMP), a measure developed for this analysis…

Read at arXiv (research papers)

arXiv (research papers) Jonas Limniatis SI

Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies

Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable…

Read at arXiv (research papers)

arXiv (research papers) Simon Hegelich SI

From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

AI coding harnesses couple language models to shells, filesystems, and network sockets, turning the harness into an automated Living-off-the-Land (LotL) platform: once an adversary injects instructions into retrieved content, dual-use binaries such as bash, curl, and find become the payload. We argue that security in agentic systems is a structural property of the cognitive architecture and permission composition rather than an emergent property of individual models. Static…

Read at arXiv (research papers)

arXiv (research papers) Wei Gu SI

TreeAgent: Structure-Aware Memory Agent for Processing Long Hierarchical Data

Practical Web applications increasingly require agents to interpret long conversations or documents. For inputs exceeding the context windows of large language models (LLMs), memory agents process segments sequentially and retain past information in bounded memory. However, they typically divide inputs into flat token segments without preserving structure or hierarchy, causing three limitations for structured data such as API responses or HTML documents. First, fixed-length…

Read at arXiv (research papers)

Google DeepMind blog SI

Opening the datasets behind our AI weather models

Foundational precipitation and geostationary satellite datasets to observe the planet clearly.

Read at Google DeepMind blog

Older stories