arXiv:2605.15976v1 Announce Type: cross Abstract: Production machine translation relies overwhelmingly on encoder-decoder Seq2Seq models, yet reinforcement learning approaches to MT fine-tuning have largely targeted decoder-only LLMs at $geq$7B parameters, with limited systematic study of encoder-decoder architectures. We apply Group Relative Policy Optimization to NLLB-200 (600M and 1.3B) using a hybrid reference-free reward (LaBSE and COMET-Kiwi) […]
Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems
arXiv:2605.15881v1 Announce Type: cross Abstract: The modeling and simulation of infinite-dimensional Hamiltonian systems are central problems in mathematical physics and engineering, however they pose significant computational and structural challenges for standard data-driven architectures. In this work, we introduce the Symplectic Neural Operator, a neural operator architecture designed to preserve the symplectic structure intrinsic to Hamiltonian […]
Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers
arXiv:2605.09403v2 Announce Type: replace-cross Abstract: Architectural choices inside the Transformer feedforward network (FFN) block do not merely affect the block itself; they reshape the computations learned by the rest of the model. We study this effect in one-layer Transformers trained on digit addition with carry, modular arithmetic, and histogram counting. Comparing dense FFNs, gated linear […]
HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation
arXiv:2605.10100v2 Announce Type: replace-cross Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $mathbbH^d$ to natively preserve the hierarchical tree topology of the human skeleton. Current state-of-the-art pose estimators aim to capture complex joint dynamics by relying on transformers and graph […]
When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
arXiv:2605.15959v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) are powerful surrogates for differential equations but are notoriously difficult to train due to spectral bias, stiffness, and poor accuracy on high-frequency or multiscale solutions. Adversarial training based on generative adversarial networks (GANs) has recently gained surprisingly strong empirical results in improving training, but the underlying […]
RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
arXiv:2605.15908v1 Announce Type: cross Abstract: Natural images are continuous, yet most generative models synthesize them on discrete grids, limiting resolution-flexible generation. Continuous neural fields enable resolution-free rendering, but prior methods introduce continuity only at the decoding stage as an interpolation module, leaving the generative latent space discretized and reconstruction-oriented. We propose RaPD (Resolution-agnostic Pixel Diffusion), […]
Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
arXiv:2605.08894v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing quantization algorithms mainly focus on improving the numerical accuracy of forward computation to eliminate performance degradation. In this paper, we show that extremely quantized LLMs suffer from systematic smoothness degradation beyond […]
RTL-BenchMT: Dynamic Maintenance of RTL Generation Benchmark Through Agent-Assisted Analysis and Revision
arXiv:2605.15537v1 Announce Type: new Abstract: This paper introduces RTL-BenchMT, an agentic framework for dynamically maintaining RTL generation benchmarks. Large Language Models (LLMs) assisted automated RTL generation is one of the most important directions in EDA research. However, current RTL benchmarks face two critical challenges: (1) flawed cases in the benchmarks and (2) overfitting to the […]
Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation
arXiv:2605.15942v1 Announce Type: cross Abstract: Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic units. We propose a Decomposed Vision-Language Alignment framework that explicitly factorizes textual prompts into a concept token and multiple attribute tokens, enabling […]
LoCO: Low-rank Compositional Rotation Fine-tuning
arXiv:2605.15916v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as an critical technique for adapting large-scale foundation models across natural language processing and computer vision. While existing methods such as low-rank adaptations achieve parameter efficiency via low-rank weight updates, they are limited in their ability to preserve the geometric structure of pretrained representations. We […]
Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation
arXiv:2605.15203v1 Announce Type: cross Abstract: We introduce Agent4POI, the first POI recommendation framework that generates context-conditioned multimodal representations at recommendation time, rather than relying on static POI embeddings pre-computed independently of context. Existing multimodal systems encode each POI once as a static embedding, a design that precludes reasoning about why the same cafe affords solo […]
Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems
arXiv:2605.16198v1 Announce Type: new Abstract: We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing to post-deployment auditing. Combining principles from formal methods with SoTA machine learning, we propose techniques that enable AI-enabled product and service developers, as well as […]