SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
arXiv:2603.12382v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent reference tracking. Existing video MLLMs...
Test-Time Strategies for More Efficient and Accurate Agentic RAG
arXiv:2603.12396v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these complexities. However, such approaches can introduce...
Revisiting Model Stitching In the Foundation Model Era
arXiv:2603.12433v1 Announce Type: cross Abstract: Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility. Prior work finds that models trained on...
Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
arXiv:2603.12458v1 Announce Type: cross Abstract: While Large Language Models (LLMs) achieve expert-level performance on standard medical benchmarks through single-hop factual recall, they severely struggle with the complex, multi-hop diagnostic reasoning required in real-world clinical settings. A primary obstacle is "shortcut...
CLARE: Classification-based Regression for Electron Temperature Prediction
arXiv:2603.12470v1 Announce Type: cross Abstract: Electron temperature (Te) is an important parameter governing space weather in the upper atmosphere, but has historically been underexplored in the space weather machine learning literature. We present CLARE, a machine learning model for predicting...
TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
arXiv:2603.12500v1 Announce Type: cross Abstract: We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs...
ELLA: Generative AI-Powered Social Robots for Early Language Development at Home
arXiv:2603.12508v1 Announce Type: cross Abstract: Early language development shapes children's later literacy and learning, yet many families have limited access to scalable, high-quality support at home. Recent advances in generative AI make it possible for social robots to move beyond...
LLM BiasScope: A Real-Time Bias Analysis Platform for Comparative LLM Evaluation
arXiv:2603.12522v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed widely, detecting and understanding bias in their outputs is critical. We present LLM BiasScope, a web application for side-by-side comparison of LLM outputs with real-time bias analysis. The...
TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
arXiv:2603.12529v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs often suffer from significant...
GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
arXiv:2603.12275v1 Announce Type: new Abstract: Unlearning knowledge is a pressing and challenging task in Large Language Models (LLMs) because of their unprecedented capability to memorize and digest training data at scale, raising more significant issues regarding safety, privacy, and intellectual...
AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents
arXiv:2603.12564v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly serve as multi-turn advisors in high-stakes domains, yet their evaluation relies on ranking-quality metrics that measure what is recommended but not whether it is safe for the user. We introduce a...
Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation
arXiv:2603.12577v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become a dominant paradigm for deploying LLMs in multi-task scenarios due to its extreme parameter efficiency. While Mixture-of-Experts (MoE) based LoRA variants have achieved promising results by dynamically routing tokens to...
Using a Human-AI Teaming Approach to Create and Curate Scientific Datasets with the SCILIRE System
arXiv:2603.12638v1 Announce Type: new Abstract: The rapid growth of scientific literature has made manual extraction of structured knowledge increasingly impractical. To address this challenge, we introduce SCILIRE, a system for creating datasets from scientific literature. SCILIRE has been designed around...
Continual Learning in Large Language Models: Methods, Challenges, and Opportunities
arXiv:2603.12658v1 Announce Type: new Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static pre-training paradigm...
Experimental evidence of progressive ChatGPT models self-convergence
arXiv:2603.12683v1 Announce Type: new Abstract: Large Language Models (LLMs) that undergo recursive training on synthetically generated data are susceptible to model collapse, a phenomenon marked by the generation of meaningless output. Existing research has examined this issue from either theoretical...
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning
arXiv:2603.12698v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving code generation in large language models, but its effectiveness is limited by weak and static verification signals in existing coding RL datasets. In...
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
arXiv:2603.12826v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk inducing reward hacking, where...
Learning from Child-Directed Speech in Two-Language Scenarios: A French-English Case Study
arXiv:2603.12906v1 Announce Type: new Abstract: Research on developmentally plausible language models has largely focused on English, leaving open questions about multilingual settings. We present a systematic study of compact language models by extending BabyBERTa to English-French scenarios under strictly size-matched...
Long-form RewardBench: Evaluating Reward Models for Long-form Generation
arXiv:2603.12963v1 Announce Type: new Abstract: The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models in various domains and scenarios. However, a significant gap remains in assessing...
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
arXiv:2603.13045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still lags behind. Existing post-training methods rely heavily on high-quality parallel data, which are...
DIALECTIC: A Multi-Agent System for Startup Evaluation
arXiv:2603.12274v1 Announce Type: cross Abstract: Venture capital (VC) investors face a large number of investment opportunities but only invest in few of these, with even fewer ending up successful. Early-stage screening of opportunities is often limited by investor bandwidth, demanding...
Multi-Step Semantic Reasoning in Generative Retrieval
arXiv:2603.12368v1 Announce Type: cross Abstract: Generative retrieval (GR) models encode a corpus within model parameters and generate relevant document identifiers directly for a given query. While this paradigm shows promise in retrieval tasks, existing GR models struggle with complex queries...
Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
arXiv:2603.12565v1 Announce Type: cross Abstract: SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This mismatch is particularly pronounced in Japanese, where spoken and written registers differ substantially in...
Generalist Large Language Models for Molecular Property Prediction: Distilling Knowledge from Specialist Models
arXiv:2603.12344v1 Announce Type: new Abstract: Molecular Property Prediction (MPP) is a central task in drug discovery. While Large Language Models (LLMs) show promise as generalist models for MPP, their current performance remains below the threshold for practical adoption. We propose...
SpectralGuard: Detecting Memory Collapse Attacks in State Space Models
arXiv:2603.12414v1 Announce Type: new Abstract: State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a critical safety vulnerability. We show that the spectral radius rho(A-bar) of the discretized transition operator governs...
Overcoming the Modality Gap in Context-Aided Forecasting
arXiv:2603.12451v1 Announce Type: new Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their...
Byzantine-Robust Optimization under $(L_0, L_1)$-Smoothness
arXiv:2603.12512v1 Announce Type: new Abstract: We consider distributed optimization under Byzantine attacks in the presence of $(L_0,L_1)$-smoothness, a generalization of standard $L$-smoothness that captures functions with state-dependent gradient Lipschitz constants. We propose Byz-NSGDM, a normalized stochastic gradient descent method with...
Curriculum Sampling: A Two-Phase Curriculum for Efficient Training of Flow Matching
arXiv:2603.12517v1 Announce Type: new Abstract: Timestep sampling $p(t)$ is a central design choice in Flow Matching models, yet common practice increasingly favors static middle-biased distributions (e.g., Logit-Normal). We show that this choice induces a speed--quality trade-off: middle-biased sampling accelerates early...
A Reduction Algorithm for Markovian Contextual Linear Bandits
arXiv:2603.12530v1 Announce Type: new Abstract: Recent work shows that when contexts are drawn i.i.d., linear contextual bandits can be reduced to single-context linear bandits. This ``contexts are cheap" perspective is highly advantageous, as it allows for sharper finite-time analyses and...
CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning
arXiv:2603.12543v1 Announce Type: new Abstract: Distributed reinforcement learning policies face network delays, jitter, and packet loss when deployed across edge devices and cloud servers. Standard RL training assumes zero-latency interaction, causing severe performance degradation under realistic network conditions. We introduce...