We consider the problem of synthesizing Clifford quantum circuits for devices with all-to-all qubit connectivity. We approach this task as a reinforcement learn...
This work revisits standard policy gradient methods used on restricted policy classes, which are known to get stuck in suboptimal critical points. We identify a...
The dominant paradigm for AI agents is an 'on-the-fly' loop in which agents synthesize plans and execute actions within seconds or minutes in response to user p...
As model families, training recipes, and compute budgets become increasingly standardized, further gains in machine learning systems depend increasingly on data...
This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation cos...
Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarant...
Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the r...
Deep learning models in medical imaging often fail when deployed in new clinical environments due to distribution shifts in demographics, scanner hardware, or a...
Large vision-language models suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven entirely by language prio...
Recent progress in automated repair of performance bugs demands realistic, executable benchmarks. However, existing C++ performance benchmarks are largely built...
On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is bene...
Shielding is a prominent model-based technique to ensure safety of autonomous agents. Classical shielding aims to ensure that nothing bad ever happens and comes...
Open-world object counting remains brittle: despite rapid advances in vision-language models (VLMs), reliably counting the objects a user intends is far from so...
Recent GPU generations deliver significantly higher FLOPs using lower-precision arithmetic, such as FP8. While successfully applied to large language models (LL...
Cross-domain few-shot medical image segmentation (CD-FSMIS) requires a model to generalise simultaneously to novel anatomical categories and unseen imaging doma...
Automated question answering (QA) over electronic health records (EHRs) demands precise evidence retrieval, faithful answer generation, and explicit grounding o...
Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational model of c...
Efficient LLM inference research has largely focused on reducing the cost of each decoding step (e.g., using quantization, pruning, or sparse attention), typica...
Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluati...
Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond recognizi...
Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency whi...
This paper demonstrates RUBEN, an interactive tool for discovering minimal rules to explain the outputs of retrieval-augmented large language models (LLMs) in d...
The RISC-V Vector Extension~(RVV) is a cornerstone for supporting compute throughout in scientific and machine learning workloads. Yet compiler support and perf...
Context. Software startups face significant challenges in building minimum viable products, particularly in the early stages, when resources are limited and exp...
Current LLM agents are proficient at calling isolated APIs but struggle with the 'last mile' of commercial software automation. In real-world scenarios, tools a...
We introduce Unitaria, a Python library that brings the simplicity of classical linear algebra toolkits such as NumPy and SciPy to the implementation of quantum...
Grey failures in the computing continuum produce ambiguous overlapping symptoms that existing approaches fail to diagnose reliably, either due to a lack of caus...
Memory-safety errors remain a persistent source of zero-day vulnerabilities in low-level software. The problem is especially acute in embedded systems, where ha...
A rapidly growing body of research is examining how LLMs influence developers when they code. To date, this research has tended to focus on productivity and cod...
Spiking Neural Networks (SNNs) can reduce energy consumption compared to conventional Artificial Neural Networks (ANNs) when spiking activity is sparse and the ...
Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the context of...
Mixture-of-Experts (MoE) serving relies on wide expert parallelism (EP) to aggregate the memory capacity and bandwidth of many GPUs within one inference instanc...
The integration of Artificial Intelligence (AI) with Distributed Ledger Technology (DLT) has become a growing research area, yet contributions tend to cluster a...
We propose a game-theoretic framework for adaptive multi-agent intelligent systems. Unlike classical game theory, which often treats strategies as primitive obj...
Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous...
Traditional federated learning (FL) relies on a central aggregator server, which can create performance bottlenecks and privacy risks. Decentralized mix-and-for...
Edge computing faces unprecedented resource orchestration challenges from multi-dimensional heterogeneity across device architectures, diverse task requirements...
Neural networks have proved an effective means of learning control policies for autonomous systems, but these learned policies are difficult to understand due t...
Cloud database systems, particularly their middleware and query execution layers, use sorting as a core operation in query processing, indexing and join executi...
Agentic artificial intelligence (AI) is a natural fit for Internet of Things (IoT) and edge systems, but edge deployments are often constrained to models around...
Byzantine Reliable Broadcast (BRB) is a fundamental primitive in distributed computing and cryptographic systems. Reducing the communication complexity of BRB p...
Existing Meta-Black-Box Optimization (MetaBBO) methods focus on how to search when controlling optimizers, but largely overlook where to search. We propose Meta...
Adaptive behavior requires the brain to transition between distinct contexts while maintaining representations of prior experience. The ability to reconfigure n...
A core challenge in program synthesis is online library learning: the incremental acquisition of reusable abstractions under uncertainty about future task deman...
Millimeter-wave (mmWave) sensing enables privacy-preserving, always-on edge perception, but its measurements are often sparse, temporally irregular, and corrupt...
Large Language Models exhibit mode collapse, producing homogeneous outputs that fail to explore valid solution spaces. We present QD-LLM, a framework for parame...
Gradient-based preference optimization methods for large language model (LLM) alignment suffer from preference collapse, converging to narrow behavioral modes w...
Spike-based encodings are sparse and energy-efficient, but have largely been formulated probabilistically, disconnected from most signal processing literature. ...
