Reducing Text Bias in Synthetically Generated MCQAs for VLMs in Autonomous Driving
arXiv:2602.17677v1 Announce Type: cross Abstract: Multiple Choice Question Answering (MCQA) benchmarks are an established standard for measuring Vision Language Model (VLM) performance in driving tasks. However, we observe the known phenomenon that synthetically generated MCQAs are highly susceptible to hidden...
Bayesian Optimality of In-Context Learning with Selective State Spaces
arXiv:2602.17744v1 Announce Type: cross Abstract: We propose Bayesian optimal sequential prediction as a new principle for understanding in-context learning (ICL). Unlike interpretations framing Transformers as performing implicit gradient descent, we formalize ICL as meta-learning over latent sequence tasks. For tasks...
ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
arXiv:2602.17867v1 Announce Type: cross Abstract: Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maximally activate a target direction, offers an alternative to costly...
BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs
arXiv:2602.17680v1 Announce Type: new Abstract: Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, general-purpose Large Language Models (LLMs) lack the capability to interpret protein sequences...
Parallel Complex Diffusion for Scalable Time Series Generation
arXiv:2602.17706v1 Announce Type: new Abstract: Modeling long-range dependencies in time series generation poses a fundamental trade-off between representational capacity and computational efficiency. Traditional temporal diffusion models suffer from local entanglement and the $\mathcal{O}(L^2)$ cost of attention mechanisms. We address these...
Provable Adversarial Robustness in In-Context Learning
arXiv:2602.17743v1 Announce Type: new Abstract: Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during pretraining. This...
Avoid What You Know: Divergent Trajectory Balance for GFlowNets
arXiv:2602.17827v1 Announce Type: new Abstract: Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. However, learning efficiency is constrained by the model's ability to...
Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models
arXiv:2602.17846v1 Announce Type: new Abstract: Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research. In particular, it is unclear...
Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning
arXiv:2602.17931v1 Announce Type: new Abstract: In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs)...
Understanding the Generalization of Bilevel Programming in Hyperparameter Optimization: A Tale of Bias-Variance Decomposition
arXiv:2602.17947v1 Announce Type: new Abstract: Gradient-based hyperparameter optimization (HPO) have emerged recently, leveraging bilevel programming techniques to optimize hyperparameter by estimating hypergradient w.r.t. validation loss. Nevertheless, previous theoretical works mainly focus on reducing the gap between the estimation and ground-truth...
With AI, investor loyalty is (almost) dead: At least a dozen OpenAI VCs now also back Anthropic
While some dual investors are understandable, others were more shocking, and signal the disregard of a longstanding ethical conflict-of-interest rule.
How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning
arXiv:2602.15580v1 Announce Type: new Abstract: When a multimodal Transformer answers a visual question, is the prediction driven by visual evidence, linguistic reasoning, or genuinely fused cross-modal computation -- and how does this structure evolve across layers? We address this question...
CARE Drive A Framework for Evaluating Reason-Responsiveness of Vision Language Models in Automated Driving
arXiv:2602.15645v1 Announce Type: new Abstract: Foundation models, including vision language models, are increasingly used in automated driving to interpret scenes, recommend actions, and generate natural language explanations. However, existing evaluation methods primarily assess outcome based performance, such as safety and...
PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
arXiv:2602.15669v1 Announce Type: new Abstract: Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human traits. We introduce PERSONA, a training-free framework that achieves...
This human study did not involve human subjects: Validating LLM simulations as behavioral evidence
arXiv:2602.15785v1 Announce Type: new Abstract: A growing literature uses large language models (LLMs) as synthetic participants to generate cost-effective and nearly instantaneous responses in social science experiments. However, there is limited guidance on when such simulations support valid inference about...
CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation
arXiv:2602.15060v1 Announce Type: cross Abstract: Long-horizon whole-body humanoid teleoperation remains challenging due to accumulated global pose drift, particularly on full-sized humanoids. Although recent learning-based tracking methods enable agile and coordinated motions, they typically operate in the robot's local frame and...
Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories
arXiv:2602.15061v1 Announce Type: cross Abstract: The emergence of Self-Driving Laboratories (SDLs) transforms scientific discovery methodology by integrating AI with robotic automation to create closed-loop experimental systems capable of autonomous hypothesis generation, experimentation, and analysis. While promising to compress research timelines...
Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning
arXiv:2602.15161v1 Announce Type: cross Abstract: Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively addressing the longstanding privacy...
Extracting Consumer Insight from Text: A Large Language Model Approach to Emotion and Evaluation Measurement
arXiv:2602.15312v1 Announce Type: new Abstract: Accurately measuring consumer emotions and evaluations from unstructured text remains a core challenge for marketing research and practice. This study introduces the Linguistic eXtractor (LX), a fine-tuned, large language model trained on consumer-authored text that...
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
arXiv:2602.15521v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promising alternative is to convert pretrained dense models into sparse MoEs....
Clinically Inspired Symptom-Guided Depression Detection from Emotion-Aware Speech Representations
arXiv:2602.15578v1 Announce Type: new Abstract: Depression manifests through a diverse set of symptoms such as sleep disturbance, loss of interest, and concentration difficulties. However, most existing works treat depression prediction either as a binary label or an overall severity score...
Causal Effect Estimation with Latent Textual Treatments
arXiv:2602.15730v1 Announce Type: new Abstract: Understanding the causal effects of text on downstream outcomes is a central task in many applications. Estimating such effects requires researchers to run controlled experiments that systematically vary textual features. While large language models (LLMs)...
Evidence-Grounded Subspecialty Reasoning: Evaluating a Curated Clinical Intelligence Layer on the 2025 Endocrinology Board-Style Examination
arXiv:2602.16050v1 Announce Type: new Abstract: Background: Large language models have demonstrated strong performance on general medical examinations, but subspecialty clinical reasoning remains challenging due to rapidly evolving guidelines and nuanced evidence hierarchies. Methods: We evaluated January Mirror, an evidence-grounded clinical...
GPSBench: Do Large Language Models Understand GPS Coordinates?
arXiv:2602.16105v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in applications that interact with the physical world, such as navigation, robotics, or mapping, making robust geospatial reasoning a critical capability. Despite that, LLMs' ability to reason about...
Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents
arXiv:2602.16246v1 Announce Type: new Abstract: Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must both reliably compare models and yield on-policy training data. Prior agentic...
Verifiable Semantics for Agent-to-Agent Communication
arXiv:2602.16424v1 Announce Type: new Abstract: Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols are...
Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
arXiv:2602.16435v1 Announce Type: new Abstract: Automated feature engineering (AFE) enables AI systems to autonomously construct high-utility representations from raw tabular data. However, existing AFE methods rely on statistical heuristics, yielding brittle features that fail under distribution shift. We introduce CAFE,...
Agent Skill Framework: Perspectives on the Potential of Small Language Models in Industrial Environments
arXiv:2602.16653v1 Announce Type: new Abstract: Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and boosting task accuracy. Based...
What Persona Are We Missing? Identifying Unknown Relevant Personas for Faithful User Simulation
arXiv:2602.15832v1 Announce Type: cross Abstract: Existing user simulations, where models generate user-like responses in dialogue, often lack verification that sufficient user personas are provided, questioning the validity of the simulations. To address this core concern, this work explores the task...
The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts
arXiv:2602.15843v1 Announce Type: cross Abstract: In "Compress or Route?" (Johnson, 2026), we found that code generation tolerates aggressive prompt compression (r >= 0.6) while chain-of-thought reasoning degrades gradually. That study was limited to HumanEval (164 problems), left the "perplexity paradox"...