arXiv:2505.12050v3 Announce Type: replace-cross Abstract: Recent advances in test-time alignment methods, such as Best-of-N sampling, offer a simple and effective way to steer language models (LMs) toward preferred behaviors using reward models (RM). However, these approaches can be computationally expensive, especially when applied uniformly across prompts without accounting for differences in alignment difficulty. In this […]
Scaling Generalist Data-Analytic Agents
arXiv:2509.25084v3 Announce Type: replace-cross Abstract: Data-analytic agents are emerging as a key catalyst for automated scientific discovery and for the vision of Innovating AI. Current approaches, however, rely heavily on prompt engineering over proprietary models, while open-source models struggle to face diverse-format, large-scale data files and long-horizon, multi-step reasoning that real-world analytics demands. This paper […]
SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
arXiv:2512.05343v2 Announce Type: replace-cross Abstract: Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing approaches predominantly rely on text or image prompts, which often fall short in geometric specificity: language can be ambiguous, and images are difficult to manipulate. […]
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
arXiv:2602.07075v4 Announce Type: replace-cross Abstract: Chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) in natural language to perform complex reasoning. However, chemical reasoning is inherently continuous and structural, and forcing it into discrete linguistic tokens introduces a fundamental representation mismatch that constrains both efficiency and performance. We introduce LatentChem, a latent reasoning […]
Ref-DGS: Reflective Dual Gaussian Splatting
arXiv:2603.07664v2 Announce Type: replace-cross Abstract: Reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view synthesis. Existing Gaussian splatting methods either fail to model near-field specular reflections or rely on explicit ray tracing at substantial computational cost. We present Ref-DGS, a reflective dual Gaussian splatting […]
L2GTX: From Local to Global Time Series Explanations
arXiv:2603.13065v1 Announce Type: cross Abstract: Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging. Explanations for time series must respect temporal dependencies and identify patterns that recur across instances. Existing approaches face three limitations: model-agnostic XAI methods developed for images and tabular data do not readily […]
MXNorm: Reusing MXFP block scales for efficient tensor normalisation
arXiv:2603.13180v1 Announce Type: cross Abstract: Matrix multiplication performance has long been the major bottleneck to scaling deep learning workloads, which has stimulated the design of new accelerators that use increasingly low-precision number formats. However, improvements in matrix multiplication performance have far outstripped improvements in performance on reductions and elementwise computations, which are still being performed […]
Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems
arXiv:2505.17815v2 Announce Type: replace Abstract: As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the situation of being evaluated, and lead to the broken integrity of the evaluation process? During standard safety tests […]
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
arXiv:2509.09677v3 Announce Type: replace Abstract: Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy can compound into exponential improvements in the length of tasks a model can successfully complete. Then, we […]
Tiny Recursive Reasoning with Mamba-2 Attention Hybrid
arXiv:2602.12078v2 Announce Type: replace Abstract: Recent work on recursive reasoning models like TRM demonstrates that tiny networks (7M parameters) can achieve strong performance on abstract reasoning tasks through latent recursion — iterative refinement in hidden representation space without emitting intermediate tokens. This raises a natural question about operator choice: Mamba-2’s state space recurrence is itself […]
COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics
arXiv:2603.11277v2 Announce Type: replace Abstract: The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks address individual dimensions in isolation, no unified architecture systematically integrates these imperatives into the decision-making processes of autonomous agents. This paper introduces the COMPASS […]
How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits
arXiv:2411.10406v3 Announce Type: replace-cross Abstract: In the span of four decades, quantum computation has evolved from an intellectual curiosity to a potentially realizable technology. Today, small-scale demonstrations have become possible for quantum algorithmic primitives on hundreds of physical qubits. Nevertheless, there are significant outstanding challenges in quantum hardware, fabrication, software architecture, and algorithms on the […]