The scalability of robotic learning is fundamentally bottlenecked by the significant cost and labor of real-world data collection. While simulated data offers a scalable alternative, it often fails to generalize to the real world due to significant gaps in visual appearance, physical properties, and object interactions. To address this, we propose RoboSimGS, a novel Real2Sim2Real framework that converts multi-view real-world images into scalable, high-fidelity, and physically interactive simulation environments for robotic manipulation. Our approach reconstructs scenes using a hybrid representation: 3D Gaussian Splatting (3DGS) captures the photorealistic appearance of the environment, while mesh primitives for interactive objects ensure accurate physics simulation. Crucially, we pioneer the use of a Multi-modal Large Language Model (MLLM) to automate the creation of physically plausible, articulated assets. The MLLM analyzes visual data to infer not only physical properties (e.g., density, stiffness) but also complex kinematic structures (e.g., hinges, sliding rails) of objects. We demonstrate that policies trained entirely on data generated by RoboSimGS achieve successful zero-shot sim-to-real transfer across a diverse set of real-world manipulation tasks. Furthermore, data from RoboSimGS significantly enhances the performance and generalization capabilities of SOTA methods. Our results validate RoboSimGS as a powerful and scalable solution for bridging the sim-to-real gap.

Context parallelism has emerged as a key technique to support long-context training, a growing trend in generative AI for modern large models. However, existing context parallel methods rely on static parallelization configurations that overlook the dynamic nature of training data, specifically, the variability in sequence lengths and token relationships (i.e., attention patterns) across samples. As a result, these methods often suffer from unnecessary communication overhead and imbalanced computation. In this paper, we present DCP, a dynamic context parallel training framework that introduces fine-grained blockwise partitioning of both data and computation. By enabling flexible mapping of data and computation blocks to devices, DCP can adapt to varying sequence characteristics, effectively reducing communication and improving memory and computation balance. Micro-benchmarks demonstrate that DCP accelerates attention by 1.19x~2.45x under causal masks and 2.15x~3.77x under sparse attention patterns. Additionally, we observe up to 0.94x~1.16x end-to-end training speed-up for causal masks, and 1.00x~1.46x for sparse masks.

Existing studies have introduced method-based reasoning and scope extension as approaches to enhance Large Language Model (LLM) performance beyond direct matrix mappings. Building on these foundations, this paper summarizes and integrates these ideas into a unified Intuition-Method Layered Model with Scope Extension, designed to address indirected (unseen) issues more systematically. In this framework, intuition-based thinking provides rapid first-reaction answers, while method-based thinking decouples questions and solutions into transferable reasoning units. Scope extension is then applied to broaden applicability, including vertical (cause analysis), horizontal (parallel and generalized issues), and for the first time, temporal and spatial extensions, which expand reasoning across time and contextual dimensions. These extensions are organized into systematic knowledge trees that interconnect into a knowledge network, thereby increasing adaptability. To quantitatively evaluate this process, we propose the entropy of method extension, which measures the independence and diversity of extensions as an indicator of the system's capacity to solve unseen questions. By logically connecting existing approaches with new extensions and introducing an entropy-based evaluation framework, this work advances toward a more robust and extensible reasoning paradigm for LLMs in real-world problem-solving.

Cross-attention transformers and other multimodal vision-language models excel at grounding and generation; however, their extensive, full-precision backbones make it challenging to deploy them on edge devices. Memory-augmented architectures enhance the utilization of past context; however, most works rarely pair them with aggressive edge-oriented quantization. We introduce BitMar, a quantized multimodal transformer that proposes an external human-like episodic memory for effective image-text generation on hardware with limited resources. BitMar utilizes 1.58-bit encoders, one for text (BitNet-style) and one for vision (DiNOv2-based), to create compact embeddings that are combined and used to query a fixed-size key-value episodic memory. During vector retrieval, the BitNet decoder applies per-layer conditioning, which increases the contextual relevance of generated content. The decoder also employs attention sinks with a sliding-window mechanism to process long or streaming inputs under tight memory budgets. The combination of per-layer conditioning and sliding-window attention achieves a strong quality-speed trade-off, delivering competitive captioning and multimodal understanding at low latency with a small model footprint. These characteristics make BitMar well-suited for edge deployment.

Reinforcement Learning (RL) has emerged as a powerful paradigm for post-training Large Language Models (LLMs), significantly enhancing their capabilities on complex, multi-step reasoning tasks (Ouyang et al., 2022). Methods based on Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) (Rafailov et al., 2023) have become standard practice for aligning LLMs. These paradigms are often powered by foundational algorithms like Proximal Policy Optimization (PPO) (Schulman et al., 2017), with state-of-the-art variants such as Group Relative Policy Optimization (GRPO) (Shao et al., 2024) pushing models to achieve remarkable performance on benchmarks like GSM8K (Cobbe et al., 2021) and MA TH (Hendrycks et al., 2021). These successes, often marked by state-of-the-art results (Lewkowycz et al., 2022; Lightman et al., 2023), are widely interpreted as a significant leap forward, suggesting that RL-based alignment is a key pathway toward developing more general and robust machine reasoning systems. Despite impressive reported gains, a key question is whether current benchmarks still meaningfully assess generalization. Our findings suggest that the traditional assumption underlying benchmark design, that a model's ability to perform well on unseen test examples is sufficient to measure generalization, no longer holds for RL. We find that RL-based reasoning models trained on the training split achieve nearly the same performance as those trained directly on the test split, indicating that "unseen-ness" alone is no longer the challenging or discriminative criterion. This calls for the rethinking of evaluation: rather than relying solely on disjoint train/test splits, future benchmarks must incorporate settings that remain sensitive to deeper forms of generalization and can reveal weaknesses that simple data separation fails to expose. To systematically investigate this phenomenon, we introduce a multi-faceted empirical framework designed not merely to measure performance, but to deconstruct it.

As large language models (LLMs) are increasingly applied in sensitive domains such as medicine and law, hallucination detection has become a critical task. Although numerous benchmarks have been proposed to advance research in this area, most of them are artificially constructed--either through deliberate hallucination induction or simulated interactions--rather than derived from genuine LLM-human dialogues. Consequently, these benchmarks fail to fully capture the characteristics of hallucinations that occur in real-world usage. To address this limitation, we introduce AuthenHallu, the first hallucination detection benchmark built entirely from authentic LLM-human interactions. For AuthenHallu, we select and annotate samples from genuine LLM-human dialogues, thereby providing a faithful reflection of how LLMs hallucinate in everyday user interactions. Statistical analysis shows that hallucinations occur in 31.4% of the query-response pairs in our benchmark, and this proportion increases dramatically to 60.0% in challenging domains such as Math & Number Problems. Furthermore, we explore the potential of using vanilla LLMs themselves as hallucination detectors and find that, despite some promise, their current performance remains insufficient in real-world scenarios.

The increasing availability of unstructured data has opened new frontiers in quantitative finance. In particular, the integration of sentiment analysis into trading strategies has gained great interest. In contrast to traditional technical indicators, which capture patterns in historical price and volume data, sentiment signals extracted from news articles and other media offer a complementary, forward-looking perspective rooted in investor expectations and market narratives. However, effectively combining these two distinct sources of information, one backward-looking and one anticipatory, remains a significant challenge in systematic investing. This paper explores an innovative approach to integrating sentiment information with traditional technical indicators in equity market trading.

Code runtime optimization--the task of rewriting a given code to a faster one-- remains challenging, as it requires reasoning about performance trade-offs involving algorithmic and structural choices. Recent approaches employ code-LLMs with slow-fast code pairs provided as optimization guidance, but such pair-based methods obscure the causal factors of performance gains and often lead to superficial pattern imitation rather than genuine performance reasoning. We introduce ECO, a performance-aware prompting framework for code optimization. ECO first distills runtime optimization instructions (ROIs) from reference slow-fast code pairs; Each ROI describes root causes of inefficiency and the rationales that drive performance improvements. For a given input code, ECO in parallel employs (i) a symbolic advisor to produce a bottleneck diagnosis tailored to the code, and (ii) an ROI retriever to return related ROIs. These two outputs are then composed into a performance-aware prompt, providing actionable guidance for code-LLMs. ECO's prompts are model-agnostic, require no fine-tuning, and can be easily prepended to any code-LLM prompt. Our empirical studies highlight that ECO prompting significantly improves code-LLMs' ability to generate efficient code, achieving speedups of up to 7.81 while minimizing correctness loss. Code runtime optimization--the task of rewriting a given code to a faster one--is a fundamental problem in software engineering, as it directly affects user experience and system performance (ISO/IEC, 2011). Recent advances in large language models for code (code-LLMs) demonstrated remarkable ability in ensuring functional correctness through tasks such as code synthesis, translation, and summarization (Chen et al., 2021; Xu et al., 2022). However, correctness alone does not imply efficiency; generating faster code requires performance-oriented reasoning that goes beyond code semantics. This gap makes code optimization particularly challenging for approaches that rely solely on the intrinsic capabilities of code-LLMs (Shypula et al., 2024). Early works in code optimization utilized compiler-driven techniques, which applied rule-based analysis at the intermediate representation level, such as dead code elimination or loop unrolling (Wegman & Zadeck, 1991; Booshehri et al., 2013). These approaches are effective for addressing well-defined low-level inefficiencies, but they fail to capture the dominant performance bottlenecks--program-level, context-dependent optimizations including algorithmic restructuring or data-structure selection. However, code-LLMs alone lack the capacity to optimize code and therefore require external guidance. Building on this, Shypula et al. (2024) and Gao et al. (2025) exploit slow-fast code pairs through prompting techniques such as in-context learning (ICL) and retrieval-augmented generation (RAG), where the example pairs are chosen randomly or by code-similarity retrieval.

Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. To bridge this gap, we introduce MARS-Sep, a reinforcement learning framework that reformulates separation as decision making. Instead of simply regressing ground-truth masks, MARS-Sep learns a factorized Beta mask policy that is optimized by a clipped trust-region surrogate with entropy regularization and group-relative advantage normalization. Concretely, we sample masks from a frozen old policy, reconstruct waveforms, and update the current policy using clipped importance ratios-yielding substantially more stable and sample-efficient learning. Multimodal rewards, derived from an audio-text-vision encoder, directly incentivize semantic consistency with query prompts. We further propose a progressive alignment scheme to fine-tune this encoder, boosting its cross-modal discriminability and improving reward faithfulness. Extensive experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation, with notable improvements in signal metrics and semantic quality. Our code is available at https://anonymous.4open.science/r/MARS-Sep. Sound separation samples are available at https://mars-sep.github.io/.

Motion planning in complex scenarios is a core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to generate trajectories, while recent approaches leverage large language models (LLMs) for decision-making. However, it remains unclear whether LLMs truly capture human driving logic. We propose Align2Act, a motion planning framework that transforms instruction-tuned LLMs into interpretable planners aligned with human behavior. We derive structured driving instructions based on human reasoning patterns (e.g., anticipate hazards, yield at intersections) and traffic rules (e.g., stop at red lights, maintain lane boundaries). Our Align2ActChain module guides step-by-step reasoning to produce both an interpretable rationale and a safe trajectory. By fine-tuning LLaMA-2-7B with LoRA on one million scenarios from the nuPlan dataset, our method achieves an open-loop score of 85.17 and closed-loop scores of 70.31 (non-reactive) and 66.96 (reactive) on Test14-random. Unlike prior work focused on synthetic or open-loop settings, we demonstrate improved planning quality and human-likeness on the real-world nuPlan closed-loop benchmark. Ablation studies confirm that structured reasoning significantly improves performance over baseline LLM planners.