arXiv AI
Jul 28
Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model
arXiv:2607. 22083v2 Announce Type: replace Abstract: We present Nanbeige4.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 28
Statistical realism is not evidence that LLMs can estimate treatment effects in social science experiments
arXiv:2604. 02458v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate human responses and estimate treatment effect of interventions when real-world experiments are costly or infeasible.
arXiv Machine Learning
Jul 28
Parallel Swin Transformer-Enhanced 3D MRI-to-CT Synthesis for MRI-Only Radiotherapy Planning
arXiv:2602. 05387v2 Announce Type: replace-cross Abstract: MRI provides superior soft tissue contrast without ionizing radiation; however, the absence of electron density information limits its direct use for dose calculation.
arXiv Machine Learning
Jul 28
LanteRn: Latent Visual Structured Reasoning
arXiv:2603. 25629v2 Announce Type: replace-cross Abstract: While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs).
arXiv Machine Learning
Jul 28
Learning to Optimize at Scale: A Benders Decomposition-TransfORmers Framework for Stochastic Combinatorial Optimization
arXiv:2607. 22550v1 Announce Type: cross Abstract: We propose a learning-augmented Benders decomposition framework to solve large-scale two-stage stochastic mixed-integer programs.
arXiv Machine Learning
Jul 28
Shift-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment
arXiv:2501. 19060v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs), such as CLIP, adapt effectively to downstream tasks through prompt tuning, but fine-tuning can misalign predictive confidence and accuracy, particularly on unseen classes.
arXiv Machine Learning
Jul 28
Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs
arXiv:2506. 03168v2 Announce Type: replace-cross Abstract: Amid the challenges posed by global population growth and climate change, traditional agricultural Internet of Things (IoT) systems is currently undergoing a significant digital transformation to facilitate efficient big data processing.
arXiv Machine Learning
Jul 28
MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation
arXiv:2509. 15357v3 Announce Type: replace-cross Abstract: Diffusion models have achieved strong results in text-to-image generation, but important limitations remain as prompts become more structured and multi-object.
arXiv Machine Learning
Jul 28
Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs
arXiv:2605. 09239v2 Announce Type: replace-cross Abstract: Large language models fail at counting how many times a word repeats in a list, even though they perform well on far harder reasoning tasks.
arXiv AI
Jul 28
LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning
arXiv:2607. 22777v1 Announce Type: cross Abstract: Protein language models learn transferable sequence representations.
arXiv AI
Jul 28
LLM-Assisted Ontology Engineering and Construction of a French Legal Knowledge Graph
arXiv:2607. 24551v1 Announce Type: new Abstract: Maintenance regulations are complex legal texts that are difficult to exploit when addressing a specific case and challenging to integrate into operational systems.
arXiv AI
Jul 28
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
arXiv:2607. 24241v1 Announce Type: cross Abstract: Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models.
arXiv AI
Jul 28
Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning
arXiv:2607. 22996v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes.
arXiv AI
Jul 28
Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning
arXiv:2607. 22732v1 Announce Type: new Abstract: LLM-based game agents often perform poorly on more complex tasks.
arXiv AI
Jul 28
Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining
arXiv:2607. 23175v1 Announce Type: cross Abstract: Reducing toxicity is often framed as a global alignment problem, yet perceptions of harmful language are subjective and context-dependent.
arXiv AI
Jul 28
Imprompt: A Language Framework for Prompt Programming
arXiv:2607. 22683v1 Announce Type: new Abstract: With the unprecedented success of Language Models (LMs), the science of Prompt Engineering has evolved the powerful idea of Prompt Programming, where prompts are treated as a programmable control surface for describing complex tasks and leveraging LM capabilities.
arXiv AI
Jul 28
Training Language Models to Cooperate with Inference-Time Controllers
arXiv:2607. 23771v1 Announce Type: new Abstract: Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning.
arXiv AI
Jul 28
MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
arXiv:2607. 24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model.
arXiv AI
Jul 28
Do Coverage and Mutation Scores of LLM-Generated Test Suites Correlate with Their Effectiveness? (Replicability Study)
arXiv:2607. 22880v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have driven growing interest in using LLMs to automate test generation.
arXiv AI
Jul 28
In-Context Learning as Implicit Policy Gradient
arXiv:2607. 23153v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) can iteratively improve their outputs by incorporating generated samples and their corresponding evaluation scores as in-context examples.