As a relatively new forum, ACM FAccT has become a key space for activists and scholars to critically examine emerging AI and ML technologies. It brings...
Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specif...
Kurtosis-based Independent Component Analysis (ICA) weakens in wide, balanced mixtures. We prove a sharp redundancy law: for a standardized projection w...
Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms....
WebGIS development requires rigor, yet agentic AI frequently fails due to five large language model (LLM) limitations: context constraints, cross-sessio...
We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements...
Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their feature representati...
Continual post-training of generative models is widely used, yet a principled understanding of when and why forgetting occurs remains limited. We develo...
The surge in reinforcement learning (RL) applications gave rise to diverse supporting technology, such as RL frameworks. However, the architectural patt...
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be...
Academic integrity continues to face the persistent challenge of examination cheating. Traditional invigilation relies on human observation, which is in...
Research in AI using Large-Language Models (LLMs) is rapidly evolving, and the comparison of their performance with human reasoning has become a key con...
Large vision--language models (VLMs) are increasingly applied to long-video question answering, yet inference is often bottlenecked by the number of inp...
Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effectiv...
Measuring LLM agent performance through trajectory analysis, benchmark suites, LLM-as-judge, failure taxonomies, and production monitoring strategies.
Implementing defense-in-depth safety for production LLM agents - prompt injection defense, input/output guardrails, tool sandboxing, HITL confirmation, and audit logging.
While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual parti...
Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipeline with min...
Many software systems originate as prototypes or minimum viable products (MVPs), developed with an emphasis on delivery speed and responsiveness to chan...
As forgery types continue to emerge consistently, Incremental Face Forgery Detection (IFFD) has become a crucial paradigm. However, existing methods typ...
We propose a novel amortized optimization method for predicting optimal transport (OT) plans across multiple pairs of measures by leveraging Kantorovich...
Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes w...
Federated learning (FL) is an effective paradigm for distributed environments such as the Internet of Things (IoT), where data from diverse devices with...
Direct Preference Optimization (DPO) is widely used after supervised fine-tuning (SFT) to align language models, yet empirical behavior under small back...
Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying sa...
Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with...
Can narratives make arguments more persuasive? And to this end, which narrative features matter most? Although stories are often seen as powerful tools...
Orofacial clefts are among the most common congenital craniofacial abnormalities, yet accurate prenatal detection remains challenging due to the scarcit...
As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results wh...
Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both co...
Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominen...
Large language models have shown strong performance on broad-domain knowledge and reasoning benchmarks, but it remains unclear how well language models...
Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases. In...
The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understan...
Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their trainin...
We introduce **CRYSTAL** (*__C__lear __R__easoning via __Y__ielded __S__teps, __T__raceability and __L__ogic*), a diagnostic benchmark with 6,372 instan...
Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities,...
Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context...
Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have...
Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed...
Active learning (AL) aims to reduce annotation costs while maximizing model performance by iteratively selecting valuable instances. While foundation mo...
Scientific discovery increasingly relies on AI systems to select candidates for expensive experimental validation, yet no principled, budget-aware evalu...
Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benc...
Firearm violence is a pressing public health issue, yet research into survivors' lived experiences remains underfunded and difficult to scale. Qualitati...
Evidence-grounded reasoning requires more than attaching retrieved text to a prediction: a model should make decisions that depend on whether the provid...
Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal re...
Conventional fine-tuning on domain-specific datasets can inadvertently alter a model's pretrained multimodal priors, leading to reduced generalization....
Competency Questions (CQs) are a cornerstone of requirement elicitation in ontology engineering. CQs represent requirements as a set of natural language...
The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Be...
Computational X-ray absorption near-edge structure (XANES) is widely used to probe local coordination environments, oxidation states, and electronic str...
LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks f...
Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-leve...
The dynamics of Saturn's satellite system offer a rich framework for studying orbital stability and resonance interactions. Traditional methods for anal...
Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a funda...
Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, acti...
Cost-per-click (CPC) in paid search is a volatile auction outcome generated by a competitive landscape that is only partially observable from any single...
Most familiar equilibrium concepts, such as Nash and correlated equilibrium, guarantee only that no single player can improve their utility by deviating...
Federated learning (FL) faces challenges in uncertainty quantification (UQ). Without reliable UQ, FL systems risk deploying overconfident models at unde...
AI agents powered by reasoning models require access to sensitive user data. However, their reasoning traces are difficult to control, which can result...
Agentic AI is increasingly judged not by fluent output alone but by whether it can act, remember, and verify under partial observability, delay, and str...
Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore...
GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong p...
Chest X-ray plays a central role in thoracic diagnosis, and its interpretation inherently requires multi-step, evidence-grounded reasoning. However, lar...
The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benc...
Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving...
Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for...
The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often originati...
Transformer models are widely deployed in critical AI applications, yet faults in their attention mechanisms, projections, and other internal components...
Engineering system design -- whether mechatronic, control, or embedded -- often proceeds in an ad hoc manner, with requirements left implicit and tracea...
The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource se...
This study presents the development of the PsyCogMetrics AI Lab (psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometri...
The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpful...
Quantization can drastically increase the efficiency of large language and vision models, but typically incurs an accuracy drop. Recently, function-pres...
Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at...
Multi-turn interactions with large language models typically retain the assistant's own past responses in the conversation history. In this work, we rev...
Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption th...
Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapte...
Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-st...
While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face signific...
Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint e...
Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive vision-...
Neural networks are hypothesized to implement interpretable causal mechanisms, yet verifying this requires finding a causal abstraction -- a simpler, hi...
Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-ba...
While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs)...
The Hyperspace Analogue to Language (HAL) model relies on global word co-occurrence matrices to construct distributional semantic representations. While...
This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training...
Accurately anticipating how complex, diverse scenes will evolve requires models that represent uncertainty, simulate along extended interaction chains,...
As corporate responsibility increasingly incorporates environmental, social, and governance (ESG) criteria, ESG reporting is becoming a legal requiremen...
Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial de...
Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging for resourc...
Large Language Models (LLMs) have been widely deployed, especially through free Web-based applications that expose them to diverse user-generated inputs...
Accurate fault detection and localization in electrical distribution systems is crucial, especially with the increasing integration of distributed energ...
Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward...
Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just th...
We present FlexiTac, a low-cost, open-source, and scalable piezoresistive tactile sensing solution designed for robotic end-effectors. FlexiTac is a pra...
Obstacle avoidance in unmanned aerial vehicles (UAVs), as a fundamental capability, has gained increasing attention with the growing focus on spatial in...
The complexity of Vietnam's legal texts presents a significant barrier to public access to justice. While Large Language Models offer a promising soluti...
While large language models (LLMs) have transformed AI agents into proficient executors of computational materials science, performing a hundred simulat...
Existing tampering detection benchmarks largely rely on object masks, which severely misalign with the true edit signal: many pixels inside a mask are u...
In this work, we study scaling limits of shallow Bayesian neural networks (BNNs) via their connection to Gaussian processes (GPs), with an emphasis on s...
We develop a theory of generalization and scaling for Mixture-of-Experts (MoE) Transformers that cleanly separates \emph{active} per-input capacity from...
Despite the remarkable empirical success of score-based diffusion models, their statistical guarantees remain underdeveloped. Existing analyses often pr...
Generalized Rapid Action Value Estimation (GRAVE) has been shown to be a strong variant within the Monte-Carlo Tree Search (MCTS) family of algorithms f...
Geochemical anomaly detection plays a critical role in mineral exploration as deviations from regional geochemical baselines may indicate mineralization...
Reliable spatial analysis in GIScience requires preserving coordinate semantics, topology, units, and geographic plausibility. Current LLM-based GIS sys...
Camera motion is a fundamental geometric signal that shapes visual perception and cinematic style, yet current video-capable vision-language models (Vid...
Transformer attention computes a single softmax-weighted average over values -- a one-pass estimate that cannot correct its own errors. We introduce \em...
The use of ML in cybersecurity has long been impaired by generalization issues: Models that work well in controlled scenarios fail to maintain performan...
Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason ab...
We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework,...
Existing research infrastructure is fundamentally document-centric, providing citation links between papers but lacking explicit representations of meth...
An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained...
Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity of translation erro...
We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for lear...
Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-...
Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging. Ex...
A thorough guide to LangChain's core abstractions, LCEL composable pipelines, LangGraph stateful workflows, LangSmith observability, and when to use LangChain vs direct API calls.
Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely by...
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where indivi...
Prior approaches for membership privacy preservation usually update or retrain all weights in neural networks, which is costly and can lead to unnecessa...
Theory of Mind (ToM) reasoning with Large Language Models (LLMs) requires inferring how people's implicit, evolving beliefs shape what they seek and how...
The Flexible Job Shop Scheduling Problem (FJSP) originates from real production lines, while some practical constraints are often ignored or idealized i...
Research on developmentally plausible language models has largely focused on English, leaving open questions about multilingual settings. We present a s...
The Normalized Transformer, or nGPT (arXiv:2410.01131) achieves impressive training speedups and does not require weight decay or learning rate warmup....
Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language...
We present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on st...
We present LiveSense - a cross-platform that transforms a commercial off-the-shelf (COTS) Wi-Fi Network Interface Card (NIC) on a laptop into a centimet...
A comprehensive guide to LlamaIndex's data-centric architecture - indices, query engines, workflows, multi-document agents, and how it compares to LangChain for RAG applications.
Electroencephalogram (EEG) signals are vital for automated seizure detection, but their inherent noise makes robust representation learning challenging....
Large Language Models (LLMs) can generate persuasive influence strategies that shift cooperative behavior in multi-agent populations, but a critical que...
Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable hu...
Large language models (LLMs) have driven substantial advances in speech language models (SpeechLMs), yielding strong performance in automatic speech rec...
The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular v...
Generative audio requires fine-grained controllable outputs, yet most existing methods require model retraining on specific controls or inference-time c...
Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained contr...
Although Automatic Speech Recognition (ASR) in Bengali has seen significant progress, processing long-duration audio and performing robust speaker diari...
Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency...
Large language model agents receive instructions from many sources-system messages, user prompts, tool outputs, and more-each carrying different levels...
Research on classroom interaction has long been divided between large-scale observation and in-depth ethnographic work. We propose a framework mapping t...
Recent work on chain-of-thought (CoT) faithfulness reports single aggregate numbers (e.g., DeepSeek-R1 acknowledges hints 39% of the time), implying tha...
Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity...
Designing memory systems for LLM agents - from in-context working memory to episodic retrieval, semantic knowledge bases, and procedural memory.
We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-ba...
Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting sign...
Multimodal LLMs can process speech and images, but they cannot hear a speaker's voice or see an object's texture. We show this is not a failure of encod...
Numerous lines of aim to control $ extit{model disagreement}$ -- the extent to which two machine learning models disagree in their predictions. We adop...
Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irre...
LLM agents as autonomous systems that reason, plan, and act using tools, memory, and multi-agent coordination.
Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models mus...
With the explosive growth of digital entertainment, automated video summarization has become indispensable for applications such as content indexing, pe...
Building systems where multiple specialized LLM agents collaborate through orchestrator-worker, pipeline, and peer-to-peer patterns using LangGraph and CrewAI.
Recognizing surgical phases and steps from video is a fundamental problem in computer-assisted interventions. Recent approaches increasingly rely on lar...
Matrix multiplication performance has long been the major bottleneck to scaling deep learning workloads, which has stimulated the design of new accelera...
Understanding natural and engineered systems often relies on symbolic formulations, such as differential equations, which provide interpretability and t...
We introduce NOBLE (Nonlinear lOw-rank Branch for Linear Enhancement), an architectural augmentation that adds nonlinear low-rank branches to transforme...
Sign languages, of any geographical or accentual variation, understandably face continuous scrutiny under the ever present popularity of verbal dictatio...
Modeling neural population dynamics is crucial for foundational neuroscientific research and various clinical applications. Conventional latent variable...
While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a 'Visual Signal Dilution' p...
Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebou...
Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Buildi...
How LLM agents handle complex multi-step tasks through plan-and-execute, hierarchical planning, self-reflection, and LangGraph-based workflows.
Explainable Artificial Intelligence (XAI) seeks to enhance the transparency and accountability of machine learning systems, yet most methods follow a on...
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool...
Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are becoming increasingly important in the me...
Predictive coding graphs (PCGs) are a recently introduced generalization to predictive coding networks, a neuroscience-inspired probabilistic latent var...
Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. I...
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforc...
Reasoning in knowledge-intensive domains remains challenging as intermediate steps are often not locally verifiable: unlike math or code, evaluating ste...
Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to mi...
While second language (L2) learners may acquire target syntactic word order, mapping this syntax onto appropriate prosodic structures remains a persiste...
Conversational generative AI is rapidly entering healthcare, where general-purpose models must integrate heterogeneous patient signals and support diver...
Pathology report generation remains a relatively under-explored downstream task, primarily due to the gigapixel scale and complex morphological heteroge...
Recovering camera parameters from images and rendering scenes from novel viewpoints have long been treated as separate tasks in computer vision and grap...
Building LLM agents that interleave reasoning traces and actions in a ReAct loop to solve multi-step tasks with tool grounding.
Engineering breakdown of the ReAct paper (Yao et al., 2022) - the foundation of every AI agent built today. Plain English, production viability rating, implementation notes.
We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which ident...
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reaso...
Generally capable agents must learn from experience in ways that generalize across tasks and environments. The fundamental problems of learning, includi...
For a risk-averse finite-horizon Markov Decision Problem, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We...
We study multiteacher knowledge distillation for low resource abstractive summarization from a reliability aware perspective. We introduce EWAD (Entropy...
Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing eas...
Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for...
From Chain-of-Thought to production agent architectures. Read the 9 most important agent papers in order — with full engineering context between each one.
We study the problem of resilient strategies in the presence of uncertainty. Resilient strategies enable an agent to make decisions that are robust agai...
Many readers today struggle to assess the trustworthiness of online news because reliable reporting coexists with misinformation. The TREC 2025 DRAGUN (...
Data assimilation is the process of estimating the time-evolving state of a dynamical system by integrating model predictions and noisy observations. It...
Reward models are central to aligning large language models (LLMs) with human preferences. Yet most approaches rely on pointwise reward estimates that o...
With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Curr...
Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet it remai...
As Large Language Models (LLMs) transition into autonomous multi-agent ecosystems, robust minimax training becomes essential yet remains prone to instab...
Safety guarantees are a prerequisite to the deployment of reinforcement learning (RL) agents in safety-critical tasks. Often, deployment environments ex...
Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based...
Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, a...
Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-mo...
Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize re...
Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content...
We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially...
Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordina...
When two agents of different computational capacities interact with the same environment, they need not compress a common semantic alphabet differently;...
Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks. However, the truthfulness of their outputs is not guarantee...
The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the wor...
Real-world Table-Text question answering (QA) tasks require models that can reason across long text and source tables, traversing multiple hops and exec...
Pure-vision GUI agents provide universal interaction capabilities but suffer from severe efficiency bottlenecks due to the massive spatiotemporal redund...
Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a lo...
This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies on...
We present SpotIt+, an open-source tool for evaluating Text-to-SQL systems via bounded equivalence verification. Given a generated SQL query and the gro...
Real-world systems must continuously adapt to novel concepts from limited data without forgetting previously acquired knowledge. While Few-Shot Class-In...
Open-world embodied agents must solve long-horizon tasks where the main bottleneck is not single-step planning quality but how interaction experience is...
AI agents increasingly operate in multi-agent environments where outcomes depend on coordination. We distinguish primary algorithmic monoculture -- base...
Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study persona...
One of the dominant paradigms in self-supervised learning (SSL), illustrated by MoCo or DINO, aims to produce robust representations by capturing featur...
Surgeons don't just see -- they interpret. When an expert observes a surgical scene, they understand not only what instrument is being used, but why it...
Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as precision medicine a...
Realistic long-horizon productivity work is strongly conditioned on user-specific computer environments, where much of the work context is stored and or...
Data plays a fundamental role in consolidating markets, services, and products in the digital financial ecosystem. However, the use of real data, especi...
Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces sig...
Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across langu...
Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often emp...
This study presents the first systematic, reference-free human evaluation of large language model (LLM) machine translation (MT) for Ancient Greek (AG)...
LLMs are increasingly used as general-purpose reasoners, but long inputs remain bottlenecked by a fixed context window. Recursive Language Models (RLMs)...
Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation off...
For each axiom of KM belief update we provide a corresponding axiom in a modal logic containing three modal operators: a unimodal belief operator $B$, a...
Conventional robot social behavior generation has been limited in flexibility and autonomy, relying on predefined motions or human feedback. This study...
Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always beneficial; some calls may be...
Enabling LLMs to invoke external tools and APIs through structured function calling, covering JSON schema design, Anthropic vs OpenAI formats, parallel tool calls, and production safety.
Building LLM tool use systems in Python -- function calling, tool schemas, execution loops, error handling, and multi-step agent patterns.
Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation....
The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches dep...
Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic...
The Room Acoustics and Speaker Distance Estimation (SDE) Challenge at ICASSP 2025 explores the effectiveness of augmented room impulse response (RIR) da...
AI-based weather forecasting now rivals traditional physics-based ensembles, but state-of-the-art (SOTA) models rely on specialized architectures and ma...
Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurat...
The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large L...
AI-powered scientific research tools are rapidly being integrated into research workflows, yet the field lacks a clear lens into how researchers use the...
With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising pr...
Explaining Machine Learning (ML) results in a transparent and user-friendly manner remains a challenging task of Explainable Artificial Intelligence (XA...
A growing number of publications address the best practices to use Large Language Models (LLMs) for software engineering in recent years. However, most...
We present a method to identify a valence-arousal (VA) subspace within large language model representations. From 211k emotion-labeled texts, we derive...
The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emphasizi...
Video agentic models have advanced challenging video-language tasks. However, most agentic approaches still heavily rely on greedy parsing over densely...
Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contrib...
Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex quer...
Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representat...
Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certain...
Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it remains unclear why...
Background: Patient-facing medical chatbots based on retrieval-augmented generation (RAG) are increasingly promoted to deliver accessible, grounded heal...
Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models. While it computes advantages based on group...
Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-righ...
Recent work interprets the linear recoverability of geographic and temporal variables from large language model (LLM) hidden states as evidence for worl...
Model poisoning attacks pose a significant security threat to Federated Learning (FL). Most existing model poisoning attacks rely on collusion, requirin...
Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $π^3$ have a computational cost t...
