Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level rewards, introducing severe reward sparsity and reward ambiguity problems. To address these issues, we propose Rubrics to Tokens (RTT), a novel rubric-based RL framework that bridges coarse response-level scores and fine-grained token-level credit assignment. RTT introduces a Token-Level Relevance Discriminator to predict which tokens in the response are responsible for a specific constraint, and optimizes the policy model via RTT-GRPO, which integrates response-level and token-level advantages within a unified framework. Furthermore, when transitioning from one-dimensional, outcome-level reward to three-dimensional reward space in the token-level rubric-based RL, we propose a novel group normalization method, called Intra-sample Token Group Normalization, to accommodate this shift. Extensive experiments and benchmarks demonstrate that RTT consistently outperforms other baselines in both instruction- and rubric-level accuracy across different models.

ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents

LLM-based agents show strong potential for long-horizon reasoning, yet their context size is limited by deployment factors (e.g., memory, latency, and cost), yielding a constrained context budget. As interaction histories grow, this induces a trade-off between retaining past information and staying within the context limit. To address this challenge, we propose Budget-Aware Context Management (BACM), which formulates context management as a sequential decision problem with a context budget constraint. It enables agents to assess the available budget before incorporating new observations and decide when and how much of the interaction history to compress. We further develop BACM-RL, an end-to-end curriculum-based reinforcement learning approach that learns compression strategies under varying context budgets. Experiments on compositional multi-objective QA and long-horizon web browsing benchmarks show that BACM-RL consistently outperforms prior methods across model scales and task complexities, achieving over $1.6\times$ gains over strong baselines in high-complexity settings, while maintaining strong advantages as budgets shrink, where most methods exhibit a downward performance trend.

Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis

In this paper, we present BAR-SQL (Boundary-Aware Reliable NL2SQL), a unified training framework that embeds reliability and boundary awareness directly into the generation process. We introduce a Seed Mutation data synthesis paradigm that constructs a representative enterprise corpus, explicitly encompassing multi-step analytical queries alongside boundary cases including ambiguity and schema limitations. To ensure interpretability, we employ Knowledge-Grounded Reasoning Synthesis, which produces Chain-of-Thought traces explicitly anchored in schema metadata and business rules. The model is trained through a two-stage process: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning via Group Relative Policy Optimization. We design a Task-Conditioned Hybrid Reward mechanism that simultaneously optimizes SQL execution accuracy-leveraging Abstract Syntax Tree analysis and dense result matching-and semantic precision in abstention responses. To evaluate reliability alongside generation accuracy, we construct and release Ent-SQL-Bench, which jointly assesse SQL precision and boundary-aware abstention across ambiguous and unanswerable queries. Experimental results on this benchmark demonstrate that BAR-SQL achieves 91.48% average accuracy, outperforming leading proprietary models, including Claude 4.5 Sonnet and GPT-5, in both SQL generation quality and boundary-aware abstention capability. The source code and benchmark are available anonymously at: https://github.com/TianSongS/BAR-SQL.

IndexTTS 2.5 Technical Report

In prior work, we introduced IndexTTS 2, a zero-shot neural text-to-speech foundation model comprising two core components: a transformer-based Text-to-Semantic (T2S) module and a non-autoregressive Semantic-to-Mel (S2M) module, which together enable faithful emotion replication and establish the first autoregressive duration-controllable generative paradigm. Building upon this, we present IndexTTS 2.5, which significantly enhances multilingual coverage, inference speed, and overall synthesis quality through four key improvements: 1) Semantic Codec Compression: we reduce the semantic codec frame rate from 50 Hz to 25 Hz, halving sequence length and substantially lowering both training and inference costs; 2) Architectural Upgrade: we replace the U-DiT-based backbone of the S2M module with a more efficient Zipformer-based modeling architecture, achieving notable parameter reduction and faster mel-spectrogram generation; 3) Multilingual Extension: We propose three explicit cross-lingual modeling strategies, boundary-aware alignment, token-level concatenation, and instruction-guided generation, establishing practical design principles for zero-shot multilingual emotional TTS that supports Chinese, English, Japanese, and Spanish, and enables robust emotion transfer even without target-language emotional training data; 4) Reinforcement Learning Optimization: we apply GRPO in post-training of the T2S module, improving pronunciation accuracy and natrualness. Experiments show that IndexTTS 2.5 not only supports broader language coverage but also replicates emotional prosody in unseen languages under the same zero-shot setting. IndexTTS 2.5 achieves a 2.28 times improvement in RTF while maintaining comparable WER and speaker similarity to IndexTTS 2.

FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems

Recent advances show that large language models (LLMs) can act as autonomous agents capable of generating GPU kernels, but integrating these AI-generated kernels into real-world inference systems remains challenging. FlashInfer-Bench addresses this gap by establishing a standardized, closed-loop framework that connects kernel generation, benchmarking, and deployment. At its core, FlashInfer Trace provides a unified schema describing kernel definitions, workloads, implementations, and evaluations, enabling consistent communication between agents and systems. Built on real serving traces, FlashInfer-Bench includes a curated dataset, a robust correctness- and performance-aware benchmarking framework, a public leaderboard to track LLM agents' GPU programming capabilities, and a dynamic substitution mechanism (apply()) that seamlessly injects the best-performing kernels into production LLM engines such as SGLang and vLLM. Using FlashInfer-Bench, we further evaluate the performance and limitations of LLM agents, compare the trade-offs among different GPU programming languages, and provide insights for future agent design. FlashInfer-Bench thus establishes a practical, reproducible pathway for continuously improving AI-generated kernels and deploying them into large-scale LLM inference.

Index-ASR Technical Report

Automatic speech recognition (ASR) has witnessed remarkable progress in recent years, largely driven by the emergence of LLM-based ASR paradigm. Despite their strong performance on a variety of open-source benchmarks, existing LLM-based ASR systems still suffer from two critical limitations. First, they are prone to hallucination errors, often generating excessively long and repetitive outputs that are not well grounded in the acoustic input. Second, they provide limited support for flexible and fine-grained contextual customization. To address these challenges, we propose Index-ASR, a large-scale LLM-based ASR system designed to simultaneously enhance robustness and support customizable hotword recognition. The core idea of Index-ASR lies in the integration of LLM and large-scale training data enriched with background noise and contextual information. Experimental results show that our Index-ASR achieves strong performance on both open-source benchmarks and in-house test sets, highlighting its robustness and practicality for real-world ASR applications.

Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification

Bayesian Neural Networks (BNNs) provide principled uncertainty quantification but suffer from substantial computational and memory overhead compared to deterministic networks. While quantization techniques have successfully reduced resource requirements in standard deep learning models, their application to probabilistic models remains largely unexplored. We introduce a systematic multi-level quantization framework for Stochastic Variational Inference based BNNs that distinguishes between three quantization strategies: Variational Parameter Quantization (VPQ), Sampled Parameter Quantization (SPQ), and Joint Quantization (JQ). Our logarithmic quantization for variance parameters, and specialized activation functions to preserve the distributional structure are essential for calibrated uncertainty estimation. Through comprehensive experiments on Dirty-MNIST, we demonstrate that BNNs can be quantized down to 4-bit precision while maintaining both classification accuracy and uncertainty disentanglement. At 4 bits, Joint Quantization achieves up to 8x memory reduction compared to floating-point implementations with minimal degradation in epistemic and aleatoric uncertainty estimation. These results enable deployment of BNNs on resource-constrained edge devices and provide design guidelines for future analog "Bayesian Machines" operating at inherently low precision.

PEVLM: Parallel Encoding for Vision-Language Models

Vision-Language Models (VLMs) have demonstrated strong performance in video-language tasks, yet their application to long video understanding remains constrained by the quadratic complexity of standard attention mechanisms. In this paper, we propose \textbf{PEVLM}, a parallel encoding strategy specifically designed to improve the prefill efficiency of VLMs without requiring model finetuning. PEVLM partitions the input into block-wise segments with a shared sink, preserves full-attention positional embeddings, and aligns attention weights to mimic full-attention distributions. This design reduces attention computation from $O((T \times N)^2)$ to $O(T \times N)$ while maintaining high accuracy. Extensive experiments on the LongVideoBench benchmark show that PEVLM achieves up to 8.37\% accuracy improvement over existing inference-efficient methods and delivers up to 7.47x speedup in attention computation and 40\% reduction in end-to-end latency. Under strict latency constraints, PEVLM significantly outperforms baselines, raising accuracy from 23.26\% to 61.03\%. These results highlight PEVLM's effectiveness for low-latency, long-context video understanding, making it well-suited for real-world applications such as autonomous driving.

Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration

Large language models (LLMs) have shown remarkable reasoning capabilities, yet aligning such abilities to small language models (SLMs) remains a challenge due to distributional mismatches and limited model capacity. Existing reasoning datasets, typically designed for powerful LLMs, often lead to degraded performance when directly applied to weaker models. In this work, we introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework that bridges the capability gap between expert reasoning trajectories and diverse SLMs. Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation via solution simulation. When expert steps surpass the student's capacity -- signaled by an Imitation Gap -- the student autonomously explores alternative reasoning paths, constrained by outcome consistency. We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency over static fine-tuning. Our method enhances supervision quality by aligning training signals with the student's reasoning capabilities, offering a scalable solution for reasoning alignment in resource-constrained models.

GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs

Geometric spatial reasoning forms the foundation of many applications in artificial intelligence, yet the ability of large language models (LLMs) to operate over geometric spatial information expressed in procedural code remains underexplored. In this paper, we address this gap by formalizing the Program-to-Geometry task, which challenges models to translate programmatic drawing code into accurate and abstract geometric reasoning. To evaluate this capability, we present GeoGramBench, a benchmark of 500 carefully refined problems organized by a tailored three-level taxonomy that considers geometric complexity rather than traditional mathematical reasoning complexity. Our comprehensive evaluation of 17 frontier LLMs reveals consistent and pronounced deficiencies: even the most advanced models achieve less than 50% accuracy at the highest abstraction level. These results highlight the unique challenges posed by program-driven spatial reasoning and establish GeoGramBench as a valuable resource for advancing research in symbolic-to-spatial geometric reasoning. Project page: https://github.com/LiAuto-DSR/GeoGramBench.