Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback
arXiv:2607.26094v1 Announce Type: new
Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard approach for aligning large language models with human preferences, but its quality is limited by static, task-agnostic reward models. This mismatch leads to sparse learning signals and...
Data Fusion and Contrastive Alignment for Unconstrained IR Molecular Structure Elucidation
arXiv:2607.26164v1 Announce Type: new
Abstract: Automated molecular structure elucidation from infrared (IR) spectroscopy data has seen significant advancements in recent years, but its broad applicability is limited by a reliance on pre-determined chemical formulas provided as auxiliary model inpu...
Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models
arXiv:2607.26173v1 Announce Type: new
Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals. When projects share a goal, we should test w...
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
arXiv:2607.26120v1 Announce Type: new
Abstract: Large Language Models (LLMs)-powered multi-agent systems are increasingly deployed in mixed-motive environments, where agents operate under asymmetric information and strategic deception due to conflicting or hidden objectives. In these settings, misa...
ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science
arXiv:2607.26155v1 Announce Type: new
Abstract: Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical question answering, structured-table reasoning, or generic scientific repositories. We introduce CL...
MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization
To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions unfold to the task, object, and interaction setting. We ask whether this execution-level variation can be learned as a reusable behavioral factor shared across ...
From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon
Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction.
We face a new epoch in computing. Hardware is changing rapidly — not just faster GPUs, but a growing range of chi...
Do Models Fake Alignment Without Clear Consequences?
arXiv:2607.24758v1 Announce Type: new
Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical deployment behaviors, a phenomenon known as alignment faking. The reasons why models fake alignment ...
Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM Agents
arXiv:2607.24759v1 Announce Type: new
Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recover. The parts most useful to that work, including dead ends and walked-back claims, are routinely e...
Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels
arXiv:2607.24762v1 Announce Type: new
Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization. Optimizing these kernels is one of the most dir...
CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Models
arXiv:2607.24763v1 Announce Type: new
Abstract: Masked diffusion language models (MDLMs) are advancing rapidly, yet the evaluation standards needed to reliably interpret their progress have not kept pace. Despite MDLMs becoming competitive with autoregressive language models, seven recent remasking...
GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models
arXiv:2607.24764v1 Announce Type: new
Abstract: The rapid growth of online grocery shopping requires recommendation systems that capture cyclical purchasing behavior and diverse user intents. Traditional item-level methods face scalability and accuracy challenges, motivating category-level recommen...
Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B
arXiv:2607.22545v1 Announce Type: new
Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single...
CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
arXiv:2607.22711v1 Announce Type: new
Abstract: LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. However, the conventional append-only trajectory architecture found in practice tightly couples file-read a...
CausalGate: Causal Importance Distillation for Transformer Module Pruning
arXiv:2607.22720v1 Announce Type: new
Abstract: Existing adaptive inference methods for Large Language Models rely on observational heuristics, such as hidden-state similarity or activation magnitudes, to drop redundant modules. However, these correlation-based metrics often fail to capture subtle,...
Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
arXiv:2607.22724v1 Announce Type: new
Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group. However, on difficult long-horizon tasks, this comparison can suffer f...
QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
arXiv:2607.22743v1 Announce Type: new
Abstract: Background and Objective: Automatic polyp segmentation supports computer-aided diagnosis and early colorectal cancer detec- tion. Centralized deep learning requires hospitals to share sensitive medical data, while federated learning preserves privacy ...
Concept-based Visual Counterfactual Explanations with Diffusion Models
arXiv:2607.22544v1 Announce Type: new
Abstract: Visual counterfactual explanations aim to answer "what minimal change to this image would flip the model's prediction?", and are increasingly important as vision models are deployed in safety-critical domains (e.g., medicine). Existing diffusion-based...
SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series
arXiv:2607.22548v1 Announce Type: new
Abstract: Data centers and their compute nodes require accurate and flexible digital twins capable of modeling the complex interplay of workloads, environmental parameters, and physical metrics. Current machine learning approaches for HPC and its telemetry typi...
QFoldAgent: An Autonomous Quantum Optimization Multi-Agent System for Protein Structure Prediction
arXiv:2607.22549v1 Announce Type: new
Abstract: Hybrid quantum-classical protein structure prediction depends strongly on Hamiltonian penalty weights, yet existing lattice-based workflows typically fix these coefficients by hand and evaluate only very short fragments in simulation. We present QFold...
Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy
arXiv:2607.22554v1 Announce Type: new
Abstract: Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in different but equivalent ways. In this work, we study how model answers change...
DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs
arXiv:2607.22555v1 Announce Type: new
Abstract: Medical diagnosis is a multi-stage process: extract facts, consult knowledge, generate a differential analysis, and select the best diagnosis with explanations. Frontier LLMs are strong generalists, but single-shot prompting often yields brittle diagn...
Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers
Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple’s most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts ...