…An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech (2026) Language-Invariant Multilingual Speaker Verification for the TidyVoice 2026 Challenge (2026) Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual…
…Evaluations on mathematical reasoning benchmarks using Qwen3 models reveal an emergent phenomenon : geometric latent reasoning induces substantially shorter generations without an explicit length objective. By replacing early explicit reasoning with continuous latent…
…Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation (2026) S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA (2026) Vector RAG vs LLM-Compiled Wiki: A…
…To make CBM measurable, we introduce BeliefTrack, a closed-world benchmark spanning Rule Discovery and Circuit Diagnosis , where a finite belief space and symbolic verifiers enable exact turn-level evaluation. BeliefTrack diagnoses…
…To this end, we first compile Themis-CodeRewardBench, a benchmark to evaluate code RMs across five preference dimensions (i.e., criteria) and eight programming languages, on which we profile 50+ code, math…
…A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version) (2026) Beyond Retrieval: A Multitask Benchmark and Model for Code Search (2026) Please give a thumbs…
…Sudong Wang , , Xiaomin Yu , Zuhao Yang , , Keming Wu , , , , , , Abstract PRISM addresses distributional drift in multimodal models by inserting a distribution-alignment stage between supervised fine-tuning and reinforcement learning with verifiable rewards…
…Reinforcement learning with verifiable rewards ( RLVR ) has shown promise for this task, yet existing methods are limited by low-confusability distractors and sparse, outcome-only reward signals that cannot supervise intermediate reasoning…
…To obtain reliable self-supervision for online learning , we identify a Generative-Discriminative Gap within LVLMs, where models exhibit higher accuracy on discriminative verification than open-ended generation. Leveraging this capability, we…
…The effectiveness of SAVE for enhancing RM training is strongly validated through rigorous empirical evaluation across six diverse benchmarks. It achieves outperforming results across all datasets while maintaining consistent improvements across three…