Frontier Research Intelligence
Preparing the latest research view.
Browse
Search and filter the research library by collection and research area. Results are URL-driven for shareable views.
Node representation learning has advanced rapidly, yet most existing methods rely on per dataset training and hyperparameter tuning. This dataset specific optimization comes from the difficulty of designing reusable graph models that generalize across diverse graph datasets. In this work, we introduce Node4All, a node representation learner applicable to arbitrary graph datasets without any dataset specific optimi...
Disentangled representation learning is a powerful paradigm for robust attribute prediction. While recent methods address attribute correlations, hidden correlations remain underexplored, where data under the value of a certain attribute exhibit underlying modes correlated with other attributes. To preserve mode information and achieve disentanglement, we jointly discover modes and enforce mode based conditional i...
Imbalanced learning addresses predictive modeling problems with underrepresented regions of the data distribution. Although widely studied in classification, imbalanced regression remains challenging because of continuous target variables and heterogeneous density distributions. Existing data level methods often rely on fixed target partitioning or synthetic sample generation without jointly considering density va...
Developing Automatic Speech Recognition (ASR) for morphologically rich, low resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a controlled, fine tuned Whisper based Assamese ASR system trained on the Mozilla Common Voice 24.0 Assamese corpus. A hardware aware optimized ...
When does a committed intermediate stage in an LLM reasoning pipeline earn its cost? Constrained Path Reasoning (CPR) pairs a source aware path hypothesis with stage level accounting. Search generates provisional states; trusted or validated invariants can constrain hard, while other proposals remain soft and revisable. CPR predicts that task compatible commitments can factor transitions, concentrate candidate mas...
Cortical visual prostheses offer a definitive therapeutic vector for profound blindness, yet their clinical efficacy is bottlenecked by low resolution pixel to electrode encoding, hardware distortion, and operating system (OS) temporal interference. We introduce the $\Psi$ $\Omega$ $\mathbf{H}$ Homological Perception Calculus, a mathematically rigorous Brain Computer Interface (BCI) architecture that models visual...
This research proposes a novel paradigm at the intersection of computational neuroscience and artificial intelligence: the architecture of sensation mapping Expert AI Systems built upon the digitized metrics of qualia—the subjective, conscious instances of first person experience. While traditional AI models process semantic tokens, they remain isolated from the qualitative "what it is like" aspect of biological e...
Human like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium specific timing, and a coherent multi turn arc. We present AnthroDial, a closed loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role conditioned sch...
Accurate classification of P300 event related potentials remains challenging due to the complex, non stationary, and low signal to noise characteristics of electroencephalography (EEG) signals in brain computer interface (BCI) systems. P300 based devices, such as the P300 speller, enable communication for patients with severe motor impairments, including those with locked in syndrome; however, reliable brain signa...
Large language model (LLM) post training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on policy distillation (OPD). However, RL relies on coarse grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits ...
Monocular foundation models provide dense geometry but usually lack a stable metric scale. This paper presents VIDAR, a visual inertial dense reconstruction framework that couples SVO+IMU odometry with Depth Anything 3. VIDAR uses the visual inertial front end as a metric anchor: it provides camera poses, scale, and a consistent world frame for aligning dense foundation model predictions across time. The foundatio...
Building long horizon robot agents requires composing closed loop pipelines perception, belief update, planning, and control whose components run at different clocks and with variable latency. Today, these systems are often assembled with ad hoc concurrency and pub/sub conventions that make timing and input consumption semantics implicit, yielding schedule dependent behavior that is hard to reproduce, debug, and r...
Pretrained machine learning (ML) models help developers build ML intensive software systems without training models from scratch. However, model repositories often provide incomplete machine readable documentation about model provenance, licenses, datasets, limitations, and external references, creating transparency and governance gaps across the AI supply chain. Artificial Intelligence Bills of Materials (AIBOMs)...
Transformer based large language models (LLMs) continue to achieve state of the art performance across various natural language processing tasks. However, their subpar performance on seemingly elementary problems, such as basic arithmetic, raises concerns about model reliability, safety, and ethical deployment. In this study, we demonstrate that the performance of a vanilla Transformer model trained on integer ari...
Longitudinal T cell receptor repertoires contain signals of clonal expansion, contraction, disappearance, and reappearance after immune perturbation. Static repertoire language models usually summarize a sample as a bag of sequences, so the sampling interval, sequencing depth, and clone presence pattern are only weakly represented. This paper presents DynImmune BERT, a continuous time repertoire model for patient ...
Speech and swallowing are complex motor sequences driven by cortico bulbar communication between motor cortex and cranial muscles. Damage to these pathways impairs strength and control of orofacial muscles, causing chronic dysarthria and dysphagia that increase social isolation, aspiration risks, and mortality. We show that motor thalamus Deep Brain Stimulation (DBS) can improve these functions after traumatic bra...
Urban intersections are among the most hazardous locations in road networks, posing significant risks to vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists. The complexity of multi agent interactions demands continuous, real time monitoring systems capable of anticipating conflicts before they escalate into crashes. We present PRISA, a modular infrastructure LiDAR framework leveraging priva...
Consciousness is often regarded as a mysterious subjective experience. However, if understood as a specifictype of information processing architecture, its mechanisms can be deconstructed, simulated, and even transferred.This paper attempts to establish a model for the thinking architecture of the entire human ethnic group, includingthe generation of autonomous consciousness (the "I"), the information architecture...
Chimeric antigen receptor T cell therapy and T cell engaging bispecific antibodies have transformed hematologic oncology, but their toxicities frequently cross organ based boundaries. Cytokine release syndrome (CRS), immune effector cell–associated neurotoxicity syndrome (ICANS), cardiovascular stress, autonomic dysregulation, sleep disruption, fatigue, and psychological distress may overlap in time and ...
Residential short term load forecasting (STLF) is challenging because household demand is heterogeneous, temporally variable, and shaped by diverse behavioural routines. This work investigates whether inferred behavioural structure can be embedded within the forecasting mechanism of a Neural Process based probabilistic model, rather than used only as an external grouping signal, for context conditioned residential...
