arXiv AI
Jun 11
ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
Fine-tuning and adaptation
LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv AI
Jun 11
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
arXiv:2606. 11324v1 Announce Type: cross Abstract: We introduce Embodied-R1.
arXiv Machine Learning
Jun 11
Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching
arXiv:2606. 11925v1 Announce Type: cross Abstract: Sign language translation (SLT) converts sign language video into spoken language text and holds significant promise for improving accessibility and enabling communication between signing and non-signing communities.
arXiv Machine Learning
Jun 11
TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data
arXiv:2606. 11844v1 Announce Type: new Abstract: Continual anomaly detection in tabular data is challenging and remains largely underexplored, particularly in settings with heterogeneous feature schemas, distribution shifts, and severe class imbalance.
arXiv Machine Learning
Jun 11
Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction
arXiv:2606. 11508v1 Announce Type: new Abstract: Accurate prediction of absorption, distribution, metabolism, and excretion (ADME) properties is critical to drug discovery, but remains challenging because ADME endpoints are noisy, interdependent, and often data-limited.
arXiv AI
Jun 11
BioDivergence: A Benchmark and Evaluation Framework for Hidden Contextual Contradictions in Biomedical Abstracts
arXiv:2606. 11208v1 Announce Type: cross Abstract: Biomedical findings often seem to conflict across studies, but many of these differences are context-dependent rather than true contradictions.
arXiv AI
Jun 11
Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
arXiv:2606. 11386v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored.
arXiv AI
Jun 11
T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking
arXiv:2606. 11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures.
arXiv AI
Jun 11
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning
arXiv:2606. 11918v1 Announce Type: new Abstract: Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks.
arXiv Machine Learning
Jun 11
Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies
arXiv:2603. 15158v2 Announce Type: replace Abstract: Addressing the domain adaptation problem becomes more challenging when distribution shifts across domains stem from latent confounders that affect both covariates and outcomes.
arXiv AI
Jun 11
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
arXiv:2606. 12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language.
arXiv AI
Jun 11
Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
arXiv:2603. 09715v2 Announce Type: replace Abstract: Visual instruction tuning is crucial for improving vision-language large models (VLLMs).
arXiv Machine Learning
Jun 11
SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration
arXiv:2606. 11348v1 Announce Type: new Abstract: Clock Tree Synthesis (CTS) is a computationally expensive stage in the physical design flow, requiring iterative EDA tool invocations to navigate a vast configuration space for optimal power, wirelength, and timing skew.
arXiv AI
Jun 11
When Roleplaying, Do Models Believe What They Say?
arXiv:2606. 11502v1 Announce Type: cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite.
arXiv AI
Jun 11
Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning
arXiv:2606. 11719v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs).
arXiv Machine Learning
Jun 11
AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
arXiv:2506. 08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures.
arXiv AI
Jun 11
MLaGA: Multimodal Large Language and Graph Assistant
arXiv:2506. 02568v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis.
arXiv Machine Learning
Jun 11
Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation
arXiv:2606. 11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy.
arXiv AI
Jun 11
Models That Know How Evaluations Are Designed Score Safer
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv AI
Jun 11
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning
arXiv:2606. 11634v1 Announce Type: new Abstract: The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length.