DualEval: Joint Model-Item Calibration for Unified LLM Evaluation

Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better reflect open-ended user interactions. We introduce DualEval, a latent model-item calibration framework that represents models and evaluation items in a shared space, jointly estimating model ability together with item difficulty and sharpness. We apply DualEval across four domains: coding, math, miscellaneous domain-knowledge tasks, and generic everyday user queries. Our evaluation uses 18 frontier LLMs, static benchmark labels, and reward-model scores validated against held-out human preferences for open-ended model responses. Empirically, our framework produces reliable and balanced model rankings, and its learned item-level profiles support downstream applications such as benchmark compression for sample-efficient evaluation and anomaly detection for contamination or outlier analysis. Overall, DualEval unifies static and arena-style evaluation through joint model-item calibration, producing model rankings and item-level diagnostics that support more sample-efficient, interpretable, and auditable evaluation pipelines.

SIMBA: ABidirectional Retrieval Forward Simulation Framework for Modeling FY-4A GIIRS Hyperspectral Infrared Radiances Toward NWP Applications

Hyperspectral infrared observations are an important data source for numerical weather prediction (NWP) because they provide rich information on the vertical structure of atmospheric temperature and humidity. However, most existing deep learning methods mainly focus on one-way retrieval from radiances to atmospheric profiles, while the reverse radiance simulation process and the consistency between atmospheric state space and radiance observation space are insufficiently considered. In this study, we propose SIMBA, a unified bidirectional retrieval-forward simulation framework for FY-4A GIIRS hyperspectral infrared radiance modeling toward NWP applications. The framework jointly performs atmospheric profile retrieval and radiance reconstruction, introduces a cycle-consistency constraint to strengthen the coupling between the two processes, and employs a bidirectional Mamba state-space module to capture long-range dependencies along pressure levels. Using collocated FY-4A GIIRS observations and ERA5 reanalysis data, the proposed method is evaluated for temperature retrieval, specific humidity retrieval, long-wave radiance reconstruction, and medium-wave radiance reconstruction. Experimental results show that SIMBA outperforms several representative deep learning baselines across both retrieval and reconstruction tasks, while ablation experiments confirm the contribution of the bidirectional design and cycle-consistency mechanism. These results demonstrate that the proposed framework is effective for joint atmospheric profile retrieval and hyperspectral infrared radiance modeling, and suggest potential for future Jacobian-related analysis and NWP-oriented extensions.

Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach

Literary translation poses unique challenges due to the scarcity of high-quality annotated data and the need to balance expression fluency with literary effect. We present a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators, each targeting a distinct quality dimension. We leverage the generated data for supervised fine-tuning and reinforcement learning. Experiments show that our generated references outperform the original ground truth for SFT by 8.65 CEA100 points. For reinforcement learning, we find that DPO leads to performance degradation in this setting, while leveraging an explicit reward model for GRPO yields an additional 1.51 point improvement. We attribute this to the stability of two-stage training and GRPO's online exploration capability. Our resulting models, LitMT-8B and LitMT-14B, achieve 67.25 and 69.07 CEA100 respectively on the MetaphorTrans English-to-Chinese literary translation benchmark, competitive with Claude Sonnet 4.5 at 68.43, and demonstrate strong generalization to out-of-domain literary work (i.e., O. Henry).

Text-attributed Graph Condensation via Text Selection and Attribute Matching

Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neural Network (GNN) and language model jointly, which leads to high space and time consumption, especially on large datasets. To mitigate this, we propose TAGSAM, a condensation method that compresses TAGs while preserving training accuracy. TAGSAM comes with two key designs, i.e., subgraph text Selection and Attribute similarity Matching, which compress the text description and graph topology of TAG, respectively. For the texts, subgraph text selection selects and merges representative text chunks from multiple related text descriptions by maximizing mutual information. For the graph topology, popular condensation methods based on Matching Training Trajectories (MTT) suffer from high variance, which hinders accuracy. Our attribute similarity matching mitigates this issue by aligning stable similarity matrices. We evaluate TAGSAM against six state-of-the-art baselines, where it showcases superior performance. For the same compressed size, TAGSAM improves upon the best-performing baseline by an average of 4.9% in accuracy. Furthermore, it maintains competitive training accuracy even when the TAG is condensed to just 1% size. Our code is available at https://github.com/SundayVHan/TAGSAM

Green Shielding: A User-Centric Approach Towards Trustworthy AI

Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well addressed by existing red-teaming efforts. We propose Green Shielding, a user-centric agenda for building evidence-backed deployment guidance by characterizing how benign input variation shifts model behavior. We operationalize this agenda through the CUE criteria: benchmarks with authentic Context, reference standards and metrics that capture true Utility, and perturbations that reflect realistic variations in the Elicitation of model behavior. Guided by the PCS framework and developed with practicing physicians, we instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis (HCM-Dx), a benchmark of patient-authored queries, together with structured reference diagnosis sets and clinically grounded metrics for evaluating differential diagnosis lists. We also study perturbation regimes that capture routine input variation and show that prompt-level factors shift model behavior along clinically meaningful dimensions. Across multiple frontier LLMs, these shifts trace out Pareto-like tradeoffs. In particular, neutralization, which removes common user-level factors while preserving clinical content, increases plausibility and yields more concise, clinician-like differentials, but reduces coverage of highly likely and safety-critical conditions. Together, these results show that interaction choices can systematically shift task-relevant properties of model outputs and support user-facing guidance for safer deployment in high-stakes domains. Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.

Sanity Checks for Agentic Data Science

Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach falsely optimistic conclusions that are difficult for users to detect. To address this, we propose a pair of lightweight sanity checks grounded in the Predictability-Computability-Stability (PCS) framework for veridical data science. These checks use reasonable perturbations to screen whether an agent can reliably distinguish signal from noise, acting as a falsifiability constraint that can expose affirmative conclusions as unsupported. Together, the two checks characterize the trustworthiness of an ADS output, e.g. whether it has found stable signal, is responding to noise, or is sensitive to incidental aspects of the input. We validate the approach on synthetic data with controlled signal-to-noise ratios, confirming that the sanity checks track ground-truth signal strength. We then demonstrate the checks on 11 real-world datasets using OpenAI Codex, characterizing the trustworthiness of each conclusion and finding that in 6 of the datasets an affirmative conclusion is not well-supported, even though a single ADS run may support one. We further analyze failure modes of ADS systems and find that ADS self-reported confidence is poorly calibrated to the empirical stability of its conclusions.

From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs

Contextual automatic speech recognition (ASR) with Speech-LLMs is typically trained with oracle conversation history, but relies on error-prone history at inference, causing a train-test mismatch in the context channel that we term contextual exposure bias. We propose a unified training framework to improve robustness under realistic histories: (i) Teacher Error Knowledge by using Whisper large-v3 hypotheses as training-time history, (ii) Context Dropout to regularize over-reliance on history, and (iii) Direct Preference Optimization (DPO) on curated failure cases. Experiments on TED-LIUM 3 (in-domain) and zero-shot LibriSpeech (out-of-domain) show consistent gains under predicted-history decoding. With a two-utterance history as context, SFT with Whisper hypotheses reduce WER from 5.59% (oracle-history training) to 5.47%, and DPO further improves to 5.17%. Under irrelevant-context attacks, DPO yields the smallest degradation (5.17% -> 5.63%), indicating improved robustness to misleading context. Our code and models are published on https://github.com/XYGuo1996/Contextual_Speech_LLMs.

HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning

Vision-Language-Action (VLA) models have shown strong performance in robotic manipulation, but often struggle in long-horizon or out-of-distribution scenarios due to the lack of explicit mechanisms for multimodal reasoning and anticipating how the world will evolve under action. Recent works introduce textual chain-of-thought or visual subgoal prediction within VLA models to reason, but still fail to offer a unified human-like reasoning framework for joint textual reasoning, visual foresight, and action prediction. To this end, we propose HALO, a unified VLA model that enables embodied multimodal chain-of-thought (EM-CoT) reasoning through a sequential process of textual task reasoning, visual subgoal prediction for fine-grained guidance, and EM-CoT-augmented action prediction. We instantiate HALO with a Mixture-of-Transformers (MoT) architecture that decouples semantic reasoning, visual foresight, and action prediction into specialized experts while allowing seamless cross-expert collaboration. To enable HALO learning at scale, we introduce an automated pipeline to synthesize EM-CoT training data along with a carefully crafted training recipe. Extensive experiments demonstrate that: (1) HALO achieves superior performance in both simulated and real-world environments, surpassing baseline policy pi_0 by 34.1% on RoboTwin benchmark; (2) all proposed components of the training recipe and EM-CoT design help improve task success rate; and (3) HALO exhibits strong generalization capabilities under aggressive unseen environmental randomization with our proposed EM-CoT reasoning.

UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment

Aligning vision-language model (VLM) outputs with human preferences in domain-specific tasks typically requires fine-tuning or reinforcement learning, both of which demand labelled data and GPU compute. We show that for subjective perception tasks, this alignment can be achieved without any model training: VLMs are already strong concept extractors but poor decision calibrators, and the gap can be closed externally. We propose a training-free post-hoc concept-bottleneck pipeline consisting of three tightly coupled stages: concept mining, multi-agent structured scoring, and geometric calibration, unified by an end-to-end dimension optimization loop. Interpretable evaluation dimensions are mined from a handful of human annotations; an Observer-Debater-Judge chain extracts robust continuous concept scores from a frozen VLM; and locally-weighted ridge regression on a hybrid visual-semantic manifold calibrates these scores against human ratings. Applied to urban perception as UrbanAlign, the framework achieves 72.2% accuracy ($κ=0.45$) on Place Pulse 2.0 across six categories, outperforming the best supervised baseline by +15.1 pp and uncalibrated VLM scoring by +16.3 pp, with full dimension-level interpretability and zero model-weight modification.

CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment

Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-streaming synthesis. High-quality dual-streaming TTS depends on accurate text--speech alignment and well-designed training sequences that balance synthesis quality and latency. Prior work often relies on GMM-HMM based forced-alignment toolkits (e.g., MFA), which are pipeline-heavy and less flexible than neural aligners; fixed-ratio interleaving of text and speech tokens struggles to capture text--speech alignment regularities. We propose CTC-TTS, which replaces MFA with a CTC based aligner and introduces a bi-word based interleaving strategy. Two variants are designed: CTC-TTS-L (token concatenation along the sequence length) for higher quality and CTC-TTS-F (embedding stacking along the feature dimension) for lower latency. Experiments show that CTC-TTS outperforms fixed-ratio interleaving and MFA-based baselines on streaming synthesis and zero-shot tasks. Speech samples are available at https://ctctts.github.io/.