arXiv subjects

Jiaming Li

Publications and source records attributed to Jiaming Li.

At least 19 recordsLinked to original sources

arXiv2026

PIVOT: Progressive Intervention via Online Teacher Correction

Reinforcement learning from verifiable rewards (RLVR) is limited by sparse outcome-level feedback on hard reasoning tasks: when all rollouts in a group fail, rewards provide no learning signal. Stronger teachers can provide additional guidance, but this raises a central question: how can such signals be incorporated into RLVR to support successful rollouts while remaining learnable for the student? We distinguish two complementary mechanisms: trajectory-level intervention, which improves access to reward-bearing trajectories, and token-level supervision, which provides dense targets to guide student learning. Our controlled experiments show that either mechanism alone can remain insufficient, motivating their combination. We therefore introduce PIVOT, which inserts teacher-generated corrections into student rollouts and applies token-level KL supervision to these segments alongside the RLVR objective. Beyond their combination, we systematically analyze where to intervene and how to supervise, yielding a recipe for effective guidance. Across hard logic games and mathematical reasoning benchmarks, PIVOT consistently outperforms existing methods, nearly doubling mean avg@8 on logic games from 19.5% for the best-performing baseline to 35.6%.

cs.CL↗

arXiv2026

Learning Ordinal Probabilistic Reward from Preferences

Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically demand costly point-wise supervision, while DRMs produce uncalibrated relative scores that lack probabilistic interpretation. To address these challenges, we introduce a novel reward modeling paradigm: Probabilistic Reward Model (PRM). Instead of modeling reward as a deterministic scalar, our approach treats it as a random variable, learning a full probability distribution for the quality of each response. To make this paradigm practical, we present its closed-form, discrete realization: the Ordinal Probabilistic Reward Model (OPRM), which discretizes the quality score into a finite set of ordinal ratings. Building on OPRM, we propose a data-efficient training strategy called Region Flooding Tuning (RgFT). It enables rewards to better reflect absolute text quality by incorporating quality-level annotations, which guide the model to concentrate the probability mass within corresponding rating sub-regions. Experiments on various reward model benchmarks show that our method improves accuracy by $\textbf{2.9%}\sim\textbf{7.4%}$ compared to prior reward models, demonstrating strong performance and data efficiency. Analysis of the score distribution provides evidence that our method captures not only relative rankings but also absolute quality.

cs.CL↗

arXiv2026

Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization

Reward-maximizing reinforcement learning (RL) is widely used to post-train stochastic diffusion and flow policies for text-to-image (T2I) generation. However, reward-maximizing RL causes policy mode collapse even under reference KL or entropy regularization, reducing the policy to a single high-reward mode. In T2I, this produces similar images and reward hacking. When extended to vision-language-action (VLA) models, the same collapse removes alternative successful strategies and weakens task and scene generalization. To address this limitation, we introduce Unified Trajectory Matching Policy Optimization (Uni-TMPO), a unified RL post-training framework for diffusion and flow policies. First, Uni-TMPO converts standardized rewards into a target distribution within each trajectory group and derives the policy distribution from trajectory log probabilities. Then, forward Kullback-Leibler optimization matches the two distributions instead of maximizing expected reward. A progress-conditioned coarse-to-fine scheduler efficiently constructs T2I trajectories. Within the unified framework, feedback-conditioned sampling uses updated observations to construct VLA trajectories. Extensive experiments show that Uni-TMPO achieves higher T2I rewards and VLA ID success rates than the strongest baselines. More importantly, it achieves the best T2I reward-diversity-efficiency trade-off and VLA generalization to held-out tasks and scenes, while real-robot evaluation demonstrates the value of multiple action strategies when the higher-reward target is blocked.

cs.CV↗

arXiv2026

CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection

Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under original, lexical-preserving, prosody-preserving, and approximately neutralised conditions. We evaluate handcrafted acoustic-feature systems, self-supervised learning (SSL) probes, and large audio language models (LALMs) on CMMA and MUStARD. For target-only Qwen3-Omni, lexical-preserving speech retains a 0.135--0.148 AUROC advantage over prosody-preserving speech after duration balancing, with cluster-bootstrap intervals above zero; alternative lexical resynthesis preserves this advantage. Acoustic interventions shift scores without consistently improving discrimination or changing binary predictions under the evaluated conditions. Context and interaction estimates vary across corpora. These findings distinguish acoustic sensitivity from sarcasm discrimination while exposing duration, identity, and transformation effects.

cs.SD↗

arXiv2026

A Data-Efficient Analytical Prior Machine Learning Framework for Sound Reduction Frequency Prediction in Helmholtz Resonators

High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expensive to generate and purely data-driven surrogates may become unreliable when simulation-labelled data are scarce. This study develops an analytical-prior learning framework that reuses a low-cost analytical model to improve data efficiency under limited high-fidelity simulation budgets. Two complementary routes are considered. When the analytical model remains available at inference, it is retained as an explicit baseline and the simulation data are used to learn only the analytical-to-simulation discrepancy. When a self-contained predictor is required, the analytical mapping is first distilled from abundant low-cost evaluations into a learned prior and then calibrated with the limited simulation data. The framework is evaluated on rectangular side-branch Helmholtz resonators using 86 simulation-labelled geometries and 8,998 non-overlapping analytical-only geometries. The analytical model achieved a mean absolute error (MAE) of 1.333 Hz. Direct support vector regression (SVR) achieved 3.375 Hz, while residual SVR reduced the MAE to 0.426 Hz. A direct multilayer perceptron (MLP) achieved 1.109 Hz, whereas analytical-prior pretraining reduced the error to 0.556 Hz with frozen-prior residual adaptation and 0.371 Hz with full-model fine-tuning. Across training budgets of 20 to 70 simulation-labelled cases, both analytical correction and analytical-prior pretraining consistently improved data efficiency relative to direct learning. These results show that analytical prior information can substantially improve high-fidelity prediction when simulation data are scarce, with explicit correction and prior distillation serving complementary deployment needs.

cs.LG↗

arXiv2026

Sinkhorn Linearization and the Spectral Proxy: Unifying the Statistical and Algorithmic Theory of Feature-Parameterized Inverse Optimal Transport via a Single Spectral Sandwich

We develop the statistical and algorithmic theory of inverse optimal transport (IOT) under the feature-parameterized cost C_theta(i,j) = -theta^T phi(i,j). The core technical contribution is the Sinkhorn linearization -- the implicit-function sensitivity of the entropic OT plan to the cost -- together with its spectral proxy, a formula that is spectrally exact yet geometrically transparent. The restricted Hessian on the tangent space satisfies the spectral sandwich (pi_min/epsilon) I <= H_T^{-1} <= (pi_max/epsilon) I, yielding the single core bound sigma_min >= (pi_min/(a_max epsilon)) sqrt(lambda_min(Sigma)) that drives the entire theory. On this core we establish four theorems and one observation. T1 (identifiability): theta is globally injective on the quotient of the gauge kernel, with dimension bound F <= (K-1)^2. T2 (sparsistency): the l1-penalized estimator recovers the true support under irrepresentability and score concentration, with exponential failure probability. T3 (well-posedness): the feature-moment map M(theta) = Phi^T x_theta is strongly monotone, and the inverse is Lipschitz with constant L <= epsilon ||Phi^T S_a||_op / (pi_min lambda_min(Sigma)). T4 (convergence): local strong convexity with mu >= pi_min^2 lambda_min(Sigma) / epsilon^2 guarantees monotone gradient descent convergence. O5 (misspecification): the estimator converges to the OT-model projection of the truth; the Holder continuity of the projection map is assessed numerically, yielding setting-dependent empirical exponents alpha_eff in (0,1).

stat.ML↗

arXiv2026

RA-FinBERT: Rule-aware LoRA adaptation for low-resource financial sentiment classification

Financial sentiment analysis converts unstructured financial news into quantitative signals that can support market analysis and decision-making. Existing work on resource-efficient financial NLP has largely focused on compressing or adapting pretrained language models, with less attention to combining contextual representations with lightweight rule-derived features. This study develops Rule-Aware FinBERT (RA-FinBERT), a parameter-efficient framework that integrates low-rank adaptation (LoRA) with three continuous VADER-derived sentiment proportions (positive, negative, and neutral) and a source-level metadata feature. The standardized four-dimensional feature vector is directly concatenated with the 768-dimensional final-layer FinBERT [CLS] representation and passed through a lightweight classification head. This design introduces only 1,024 additional trainable weights relative to a structurally matched text-only FinBERT model. RA-FinBERT was evaluated against text-only FinBERT and a lightweight DistilBERT baseline for three-class sentiment classification of financial-news titles and descriptions. On the held-out test set, RA-FinBERT achieved 69.89% accuracy and a macro F1 score of 0.634, compared with 63.44% and 0.526 for text-only FinBERT. Neutral-class recall increased from 18.18% to 45.45%. The framework supports both CPU and GPU execution, offering a lightweight and practical approach to financial sentiment classification under constrained computational resources. These findings indicate that rule-derived sentiment information and source metadata can provide complementary signals to contextual FinBERT representations and improve performance with minimal additional model complexity.

cs.CL↗

arXiv2026

Orbital-Dependent Dimensional Crossover of a $p$-Wave Feshbach Resonance

We report the observation of a dimensional crossover of a $p$-wave Feshbach resonance in an ultracold, spin-polarized $^6$Li Fermi gas confined by a one-dimensional optical lattice. Using high-resolution atom-loss spectroscopy, we resolve the orbital doublet associated with the $\ml=0$ and $|\ml|=1$ scattering channels over a wide range of lattice depths. In the weak-confinement regime, the atom loss signal associated with the $|\ml|=1$ branch is stronger, consistent with the twofold orbital degeneracy of the three-dimensional system. As the lattice confinement increases, the relative loss weight of the two orbital branches evolves continuously toward the quasi-two-dimensional limit, indicating a progressive suppression of relative motion along the lattice direction. In addition, we observe a systematic confinement dependence of the orbital splitting between the two resonance branches. These results provide an experimental characterization of orbital-dependent $p$-wave scattering in reduced dimensions and motivate future microscopic studies of confined anisotropic scattering.

cond-mat.quant-gas↗

arXiv2026

Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models

Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability. Existing training methods inherit the Block Training paradigm from LLM pre-training, which introduces destructive gradient noise in instruct models due to attention leakage from unrelated contexts. Using GSNR analysis, we theoretically characterize this issue and propose Finetuning-aligned Sequential Training (FAST), a sequential training paradigm specifically designed for instruct models. FAST aligns SAE training with the data distribution and activation patterns of instruct models, substantially improving both reconstruction fidelity and feature interpretability. Experimental results show that FAST achieves higher GSNR, a significantly lower log-scaled MSE of 0.6468 compared to the baseline's 5.1985, and a near-zero Delta Loss (-0.51\% to 0.37\%). Moreover, on Llama-3.2-3B-it, FAST produces 21.1\% high-quality features, substantially outperforming baseline methods that achieve 7.0\% and 10.2\%. We further find that intervening on special token activations through SAEs can improve generation quality, revealing new opportunities for fine-grained control. Our codes are available as open source at https://github.com/Geaming2002/FAST.

cs.CL↗

arXiv2026

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming, however existing RLVR methods often suffer from sparse reward signals and unstable policy gradient updates inherent to RL-based approaches. To address the challenges, we propose PACS, a novel RLVR framework that achieves imPlicit Actor Critic coupling via a Supervised learning framework. By treating the outcome reward as a predictable label, we reformulate the RLVR problem into a supervised learning task over a score function parameterized by the policy model and optimized using cross-entropy loss. A detailed gradient analysis shows that this supervised formulation inherently recovers the classical policy gradient update while providing more stable and efficient training. Extensive experiments demonstrate that PACS significantly outperforms strong open-source models and RLVR baselines, yielding substantial average gains of +8.26% (4B) and +9.57% (8B) over base models offering a promising avenue for LLMs post-training with verifiable rewards. Our code and data are available as open source at https://github.com/ritzz-ai/PACS.

cs.CL↗

arXiv2026

Orca: The World is in Your Mind

We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community.

cs.CV↗

arXiv2026

TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing visual mode collapse and amplifying unreliable rewards. We identify the root cause as the mode-seeking nature of these methods, which maximize expected reward without effectively constraining probability distribution over acceptable trajectories, causing concentration on a few high-reward paths. In contrast, we propose Trajectory Matching Policy Optimization (TMPO), which replaces scalar reward maximization with trajectory-level reward distribution matching. Specifically, TMPO introduces a Softmax Trajectory Balance (Softmax-TB) objective to match the policy probabilities of K trajectories to a reward-induced Boltzmann distribution. We prove that this objective inherits the mode-covering property of forward KL divergence, preserving coverage over all acceptable trajectories while optimizing reward. To further reduce multi-trajectory training time on large-scale flow-matching models, TMPO incorporates Dynamic Stochastic Tree Sampling, where trajectories share denoising prefixes and branch at dynamically scheduled steps, reducing redundant computation while improving training effectiveness. Extensive results across diverse alignment tasks such as human preference, compositional generation and text rendering show that TMPO improves generative diversity over state-of-the-art methods by 9.1%, and achieves competitive performance in all downstream and efficiency metrics, attaining the optimal trade-off between reward and diversity.

cs.LG↗

arXiv2026

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation

Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. To address this issue, some approaches have introduced inference-time interventions, such as contrastive decoding, to reduce overreliance on language priors. However, these approaches overlook hallucinations stemming from position bias and spurious inter-modality correlations. In this paper, we propose a Cross-Modal Attention Calibration (CMAC) method to mitigate hallucinations in LVLMs in a training-free manner. In this method, we design an Inter-Modality Decoding (IMD) module to alleviate hallucination by a novel contrastive decoding mechanism. IMD masks the value vectors associated with significant cross-modal attention weights as distortion, which addresses both uni-modality overreliance and misleading inter-modality correlations. Additionally, a Cross-Modal Position Calibration (CMPC) module shrinks the position gap of image tokens, alleviating the position bias in cross-modal attention. Experimental results on diverse hallucination benchmarks validate the superiority of our method over existing state-of-the-art techniques in reducing hallucinations for LVLM. Our code will be available at https://github.com/lijm48/IMCCD.

cs.CV↗

arXiv2026

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

Streaming video reasoning requires models to operate in a setting where history grows without bound while meaningful evidence remains scarce. In such a landscape, relevant signal is like an oasis-small, critical, and easily lost in a desert of redundancy. Enlarging memory only widens the desert; aggressive compression dries up the oasis. The real difficulty lies in discovering where to look, not how much to remember. We therefore introduce OASIS, a novel framework for streaming video reasoning that tackles this challenge through structured, on-demand retrieval. It organizes streaming history into hierarchical events and performs reasoning as controlled refinement-short-context inference first, followed by semantically grounded retrieval only when uncertainty arises. As the retrieval is driven by high-level intent rather than embedding similarity, the retrieved memory is substantially more accurate and less noisy. Additionally, the mechanism is plug-and-play, training-free, and readily attaches to different streaming MLLM backbones. Experiments across multiple benchmarks and backbones show that OASIS achieves strong gains in long-horizon accuracy and compositional reasoning with bounded token cost and low request delay. Code is available at https://github.com/Solus-sano/OASIS.

cs.CV↗

arXiv2026

Edge-Side Residual Timing and Frequency Control for Software-Defined Ground Stations in 5G NTN Uplinks

This paper studies a ground-segment implementation problem in 5G non-terrestrial networks (NTN): once UE-side geometric pre-compensation has produced a coarse timing/frequency prior, can an edge-side residual loop keep the uplink inside an NR-feasible operating region under rapid LEO dynamics? We examine this question with a software-defined ground station (SDGS) design that keeps the coarse prior at the UE and closes the residual timing-advance (TA) / carrier-frequency-offset (CFO) loop at the ground-station edge. This paper takes a systems-and-control view rather than proposing a full-stack intelligent architecture. Its evidence base consists of a March 2026 hardware-in-the-loop (HIL) campaign and a companion uncertainty analysis. The HIL campaign includes same-window reference runs collected on the same platform with edge residual control disabled, but it does not include a cloud-loop benchmark. The placement claim is therefore architectural and control-oriented rather than a head-to-head cloud-versus-edge proof. In the Shenzhen steady-state tracking interval, the edge-controlled mode lowers mean RTT from 70.51 +/- 2.34 ms to 32.84 +/- 2.56 ms and, within the retained Layer-3 transport mapping, improves artifact-level goodput from 80.14 +/- 0.14 Mbps to 196.04 +/- 1.87 Mbps relative to that reference configuration. Across four ground-station locations, the closed-loop controller keeps residual TA P95 at 0.49 us and residual CFO P95 within 76-77 Hz. Together with the uncertainty analysis, these observations support a bounded claim: an edge-side residual timing/frequency loop can keep the SDGS uplink in a more stable NR-feasible operating regime under the assumptions retained in the current HIL artifact.

cs.NI↗

arXiv2026

I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing

Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tasks that require precise local control and complex multi-object spatial reasoning. This paradigm is severely limited by 1) the implicit coupling of planning and execution, 2) the lack of object-level control granularity, and 3) the reliance on unstructured, pixel-centric modeling. To address these limitations, we propose I2E, a novel "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment. I2E utilizes a Decomposer to transform unstructured images into discrete, manipulable object layers and then introduces a physics-aware Vision-Language-Action Agent to parse complex instructions into a series of atomic actions via Chain-of-Thought reasoning. Further, we also construct I2E-Bench, a benchmark designed for multi-instance spatial reasoning and high-precision editing. Experimental results on I2E-Bench and multiple public benchmarks demonstrate that I2E significantly outperforms state-of-the-art methods in handling complex compositional instructions, maintaining physical plausibility, and ensuring multi-turn editing stability.

cs.CV↗

arXiv2026

GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection

Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in fine-grained settings due to the semantic entanglement of subjects and attributes in pretrained vision-language model (VLM) embeddings -- leading to over-representation of attributes, mislocalization, and semantic drift in embedding space. We propose GUIDED, a decomposition framework specifically designed to address the semantic entanglement between subjects and attributes in fine-grained prompts. By separating object localization and fine-grained recognition into distinct pathways, HUIDED aligns each subtask with the module best suited for its respective roles. Specifically, given a fine-grained class name, we first use a language model to extract a coarse-grained subject and its descriptive attributes. Then the detector is guided solely by the subject embedding, ensuring stable localization unaffected by irrelevant or overrepresented attributes. To selectively retain helpful attributes, we introduce an attribute embedding fusion module that incorporates attribute information into detection queries in an attention-based manner. This mitigates over-representation while preserving discriminative power. Finally, a region-level attribute discrimination module compares each detected region against full fine-grained class names using a refined vision-language model with a projection head for improved alignment. Extensive experiments on FG-OVD and 3F-OVD benchmarks show that GUIDED achieves new state-of-the-art results, demonstrating the benefits of disentangled modeling and modular optimization. Our code will be released at https://github.com/lijm48/GUIDED.

cs.CV↗

arXiv2026

Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM

This study presents a Secure Multi-Tenant Architecture (SMTA) combined with a novel concept Burn-After-Use (BAU) mechanism for enterprise LLM environments to effectively prevent data leakage. As institutions increasingly adopt LLMs across departments, the risks of data leakage have become a critical security and compliance concern. The proposed SMTA isolates LLM instances across departments and enforces rigorous context ownership boundaries within an internally deployed infrastructure. The BAU mechanism introduces data confidentiality by enforcing ephemeral conversational contexts that are automatically destroyed after use, preventing cross-session or cross-user inference. The evaluation to SMTA and BAU is through two sets of realistic and reproducible experiments comprising of 127 test iterations. One aspect of this experiment is to assess prompt-based and semantic leakage attacks in a multi-tenant architecture (Appendix A) across 55 infrastructure-level attack tests, including vector-database credential compromise and shared logging pipeline exposure. SMTA achieves 92% defense success rate, demonstrating strong semantic isolation while highlighting residual risks from credential misconfiguration and observability pipelines. Another aspect is to evaluate the robustness of BAU under realistic failure scenarios (Appendix B) using four empirical metrics: Local Residual Persistence Rate (LRPR), Remote Residual Persistence Rate (RRPR), Image Frame Exposure Rate (IFER), and Burn Timer Persistence Rate (BTPR). Across 72 test iterations, BAU achieves a 76.75% success rate in mitigating post-session leakage threats across the client, server, application, infrastructure, and cache layers. These results show that SMTA and BAU together enforce strict isolation, complete session ephemerality, strong confidentiality guarantees, non-persistence, and policy-aligned behavior for enterprise LLMs.

cs.CR↗