arXiv subjects

Fan Yang

Publications and source records attributed to Fan Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

PSR~B0355+54: An Unexpected Compendium of Nearly All Scintillation Arc Morphologies

Scintillation arcs are sensitive probes of multipath propagation, offering a window into the distribution of scattering material in the interstellar medium. Contrary to the common observational finding that individual pulsars exhibit only a limited range of scintillation arc morphologies, we report that PSR~B0355+54, observed simultaneously at 2.25/8.60~GHz with the Shanghai Tianma Radio Telescope, displays nearly the full range of known arc patterns, many of which evolve rapidly. Across 54 observations from 2020 to 2026, we detect scintillation arcs in 53/53 usable observations at 2.25~GHz and 33/49 at 8.60~GHz. At 2.25~GHz, the secondary spectra exhibit five broad morphological types: forward arcs, inverted arclets, diffuse arcs, diffuse power, and irregular structures, with prominent displaced arclets appearing in several observations. In contrast, the 8.60-GHz spectra are generally dominated by faint forward arcs. Despite these marked morphological differences, the scaled curvatures and their annual variations agree between the two frequencies, showing that both trace the same dominant scattering screen at a fractional distance of $s=0.069^{+0.015}_{-0.014}$ near the pulsar, further supporting a possible association with the \ion{H}{ii} region Sh~2-205. Simulations show that this diversity can arise from variations in the scattered-image distribution within this screen, while brightness reconstructions at 2.25~GHz resolve localized structure down to $\sim0.02~\mathrm{mas}$. Tracking four arclets over 10~h at 8.60~GHz, including two displaced arclets, reveals a common evolutionary trend consistent with the line of sight sweeping across small-scale scattering structure, helping explain the rapid arc evolution.

astro-ph.GA↗

arXiv2026

RealControlBench: A Benchmark for Interpretability-Informed Fine-Grained Control of LLMs and Agents

Existing steering benchmarks are built around simplified, isolated generation tasks and evaluate a single behavioral attribute under controlled settings that do not reflect the diversity and complexity of practical deployment. As a result, performance on these benchmarks provides only a limited picture of how steering methods perform in the real world. We therefore introduce RealControlBench, a comprehensive benchmark for evaluating fine-grained steering of LLMs and LLM agents across diverse behavioral targets and interaction settings. RealControlBench extends steering evaluation beyond isolated generations to complex, execution-grounded, multi-turn agent interactions, covering five complementary dimensions: instruction-following control, agentic tool-use decision control, reasoning-performance steering, reasoning-length control, and trajectory-conditioned safety awareness. Rather than measuring steering success alone, the benchmark jointly evaluates target controllability and capability preservation, including instruction following, reasoning performance, and downstream agent utility and safety. It further examines whether steering effects remain specific and robust across prompt variations, domains, and model architectures. Our evaluation shows that existing steering methods remain unreliable across realistic control objectives: they often fail to consistently induce the intended behavior and can substantially degrade the model's underlying task performance. These results suggest that strong steering effects in controlled settings do not necessarily translate into reliable control in more realistic evaluations. By providing a unified, model-agnostic steering evaluation framework, RealControlBench aims to support the development of steering methods that are not only effective but also precise, robust, and useful in realistic AI deployments.

cs.CL↗

arXiv2026

Localization Lengths for Two-Dimensional Random Band Matrices: Stretched-Exponential Lower Bounds

We consider $N \times N$ random band matrices $H = (H_{xy})$ with centered complex Gaussian entries, indexed by points $x,y$ on the two-dimensional discrete torus $(\mathbb{Z} / \sqrt{N} \mathbb{Z})^2$. The matrix entries $H_{xy}$ vanish whenever the distance between $x$ and $y$ exceeds a constant multiple of the bandwidth parameter $W$. We prove that, for any fixed $\varepsilon>0$, if $W\geq(\log N)^{2+\varepsilon}$, then all bulk eigenvectors are delocalized with high probability. Equivalently, this yields a lower bound of order $\exp(W^{1/2-\varepsilon})$ on the localization length of two-dimensional random band matrices for arbitrarily small constant $\varepsilon>0$, improving the superpolynomial lower bound $W^C$ for every fixed constant $C>0$ established in arXiv:2503.07606. A key ingredient of our proof is a new strategy that closes the resolvent flow analysis using only loop observables of order at most two, without relying on the higher-order loop hierarchy.

math.PR↗

arXiv2026

Rep2Text: Decoding Full Text from a Single LLM Token Representation

Large language models represent text as hidden numerical patterns, but what information these representations actually contain remains a mystery. Can we recover the original text from just one of them? In this paper, we introduce Rep2Text, a method designed to answer this question by reconstructing text from a single hidden representation. We find that these representations preserve much more information than we might expect. For short texts of about 16 words, Rep2Text can recover roughly half of the original words while preserving their overall meaning. As the text gets longer, recovering the exact wording becomes harder, but the main ideas can still be recovered. These findings offer a new way to understand what language models store internally and highlight potential privacy risks, as hidden representations may reveal parts of the original input.

cs.CL↗

arXiv2026

Workplace Ambiguity and Technology Support for Autistic and IDD Workers

Workplace ambiguity, where expectations, evaluations, or procedures are left unstated, acts as a structural access barrier for autistic and IDD workers, routinely forcing them to act on guesses. To investigate how these barriers operate, we interviewed 11 caregivers, concluding with an AI co-design activity to explore technological solutions. Their perspectives revealed five themes of workplace ambiguity, which we synthesize into a conceptual framework comprising three intersecting dimensions: evaluative, procedural, and relational. To address these barriers, participants proposed three forms of technology support, including ambient real-time redirection, feedback processing, and physiological guidance, designed to make hidden expectations perceptible and actionable. However, this exposes a core tension: technologies designed to make the workplace legible can inadvertently make the worker hyper-legible to employers through surveillance. We argue that ambiguity-aware workplaces must make expectations explicit before they carry consequences, and assistive technologies must remain accountable to the worker.

cs.HC↗

arXiv2026

Beyond What Is Visible: Context-Aware Sentiment Across Online Communities Among Crisis Events

Social media offers timely insight into disaster experiences, yet online communities may not represent those affected on the ground. Uneven participation can bias crisis information systems toward data-rich locations and obscure communities with fewer digital traces. We address this with an adaptive cross-community learning framework that combines text and aggregate mobility signals with socioeconomic and hazard-informed community representations, supplementing sparse local observations with evidence from structurally related cities. We evaluate the framework on the January 2025 Southern California wildfires and 2024 Hurricane Helene in Florida. The adaptive model achieves the highest F1-score in both cases (0.5923 and 0.7615), while augmentation has its strongest effect where original observations are limited. The framework also reveals finer cross-city community-level sentiment variation and stronger sentiment-mobility correspondence than text-only models, with relationships differing across disaster contexts. These findings support crisis systems that better account for context-dependent evidence and improve interpretation of underrepresented community signals.

cs.CY↗

arXiv2026

SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection

Agentic reinforcement learning (RL) enables large language models (LLMs) to learn from multi-turn interactions with verifiable outcomes. Textual skills can improve exploration by distilling prior interactions into reusable guidance. However, existing skill-based RL approaches often either assume skill injection is beneficial or rely on indirect feedback or rollout-intensive evaluation to assess its utility. Our pilot studies show that rollout-based utility estimation for skill credit assignment is costly and unstable under limited sampling, while skill benefits vary across candidates and depend on the current policy's competence on each query. To address these challenges, we introduce SkillScaffold, a policy-adaptive training scaffold that combines low-cost skill-utility estimation with selective skill injection. By reusing outcome-verified training trajectories, SkillScaffold generates candidate skills and estimates their utility through outcome-aware likelihood comparisons, without candidate-specific environment rollouts. The resulting utility guides whether and which skill to inject, retaining skill-free execution when no candidate is estimated to help. Joint training enables the Generator to produce skills tailored to the evolving Executor. Scaffolded RL encourages skill internalization for skill-free inference. Experiments on ALFWorld, WebShop, ScienceWorld, and $τ^2$-Bench demonstrate gains over strong agentic-RL and skill-based RL baselines across both short- and long-horizon tasks. Ablations and further analyses support the importance of utility-based selection and abstention. Our code is available at https://github.com/Vaidurya00/SkillScaffold.

cs.LG↗

arXiv2026

Who Improves the Robot? Toward Physical Recursive Self-Improvement

Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI), in which physical experience guides lasting updates to both a robot's capabilities and its improvement procedure, making subsequent improvement more effective across tasks. Physical RSI faces challenges from noisy observations, continuous dynamics, costly trials, and irreversible consequences. We present an L0-L5 framework that differentiates capability-level from meta-level updates and within-task from across-task gains, reserving L5 for independently verified recursive gain. We study existing methods around harness adaptation and model training, alongside safety and control mechanisms that govern execution and successive updates. Our analysis reveals that, despite substantial progress in self-improvement, the surveyed literature does not yet demonstrate Physical RSI as defined by our framework. We identify research priorities in reliable feedback, causal attribution, safety preservation, and benchmarking, outlining a path toward robots that autonomously improve how they learn while ensuring safety. The GitHub repository for Physical RSI is available at https://github.com/SAIL-Research-Lab/Physical-RSI.

cs.AI↗

arXiv2026

RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory

Large language model (LLM) agents are increasingly organized into multi-agent systems for complex reasoning and decision-making tasks. However, scaling such systems can substantially increase inference cost, especially when multiple agents repeatedly process overlapping or role-irrelevant context. Many existing multi-agent frameworks focus on orchestration and role specialization, but still rely on full-context sharing or static context routing, leading to redundant token consumption, increased runtime, and inefficient memory utilization. We present \emph{Role-Conditioned Context Routing (RCR)}, an execution-time layer that allocates role-relevant shared-memory items to agents under token budgets. Given a structured shared memory and a set of role-specialized agents, RCR selectively routes task-relevant memory items to each agent according to its role, optional task-stage metadata, and token budget. RCR integrates role-conditioned relevance scoring, token-budgeted memory selection, and iterative memory updates to reduce redundant context exposure during multi-agent execution. Experiments on multi-hop QA, embodied reasoning (ALFWorld), and web-based decision-making (WebShop) show that RCR reduces token usage by 35\% on average and runtime by 38\% on average relative to Full-Context, while maintaining or improving task performance.

cs.CL↗

arXiv2026

Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction

Robot sensor designs, particularly tactile sensors, are highly diverse and evolve rapidly. Modeling each sensor in simulation demands substantial domain expertise and computational approximations can degrade the fidelity of the simulated signals. We propose Sim2Real via Bottlenecked Latent Reconstruction (SBLR), a framework that avoids sensor-specific simulation entirely by (1) training policies on a simulator-native oracle sensor that is easy to construct without modeling any particular sensor (e.g. we use a point-cloud and finger-tip forces as a tactile oracle), and (2) aligning real sensor latent embeddings to those of the oracle sensor at inference time. Policy training proceeds in two-stage: the policy first learns from the oracle sensor latents, then a bottlenecked latent reconstruction adapts it to the information loss expected when using the real sensor instead of the oracle. The alignment between oracle and real sensor is learned from unpaired random-play data collected in both simulation and the real world, using rectified-flow-based transformation networks trained on nearest-neighbor pseudo-pairs. Simulation experiments on three contact-rich tasks show that SBLR matches or approaches the performance of an oracle with direct access to tactile simulation. Hardware experiments on Peg Insertion and Gear Meshing with GelSight Mini and DIGIT sensors demonstrate 85-97.5% zero-shot success without requiring any sensor-specific modeling or calibration, outperforming a physics-based tactile simulation baseline by 7.5-15%.

cs.RO↗

arXiv2026

Before Attention Sinks Form: Hidden-State Geometry Reveals and Modulates Their Formation

Attention sinks are usually studied after they have formed. We ask whether a measurable hidden-state change appears beforehand and whether changing that geometry alters what happens later. To remove network depth as a shortcut, we compare prompts in the same model and at the same layer. When sink timing varies across prompts, simple spectral summaries of the hidden states add information beyond current attention, with the clearest prompt-specific signal in a short window about two to three layers before sink formation. The predictive strength varies across cohorts, so we treat the spectrum as a readout of a pre-sink state change rather than a universal warning statistic. The signal is broader than one measured extreme activation. We then modify only the singular values of the post-layer hidden states after current attention has already been computed. These interventions change later sink behavior in Qwen2.5, GLM-Z1, and GPT-OSS relative to norm-matched random spectral perturbations. In Qwen2.5, the immediate suppressive effect is accompanied by a reduction in next-layer query--key preference for position~0, and the learned spectral directions remain stable when estimated from substantially less training data. Together, the results show that attention sinks are preceded by a short spectral reorganization of hidden states, and directly perturbing this geometry can causally alter subsequent sink formation.

cs.LG↗

arXiv2026

Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning

Recent multimodal large language models achieve promising results on visual reasoning tasks, approaching human-level performance on existing STEM benchmarks. However, these capabilities degrade under complex real-world scenes. We identify that chain-of-thought reasoning remains largely confined to the linguistic space, rarely anchoring each step in visual evidence. The main cause is the absence of such data during training. In this work, we introduce a training data augmentation pipeline, \textbf{Visual Augmentation Primitives} (VAP), which leverages state-of-the-art vision generative models to synthesize diverse photorealistic training samples and corresponding reasoning text. VAP introduces some basic operators and applies them to a seed image and gets a variant. It also constructs coherent multimodal reasoning chains throughout the generation process. Such training data force models to perceive visual content and perform logical reasoning according to them at every step. We further introduce multimodal chain-of-thought rubric-based reinforcement learning to enhance this. It rewards not only text reasoning but also visual reasoning by scoring intermediate reasoning steps for logical validity, completeness, and consistency. Moreover, we construct the UNREAL benchmark to systematically evaluate visual reasoning on hyperrealistic scenes across controllable difficulty levels. Experiments show that a 4B model built on this framework surpasses 8B baselines, with performance improving consistently as the model scales to 32B, validating the scaling law for visual reasoning.

cs.CV↗

arXiv2026

HarnessWAM: Bridging Prediction and Deliberation in World Action Models

World Action Models~(WAMs) jointly learn environmental dynamics and robot actions, introducing priors over physical evolution into embodied control. However, finite-horizon prediction and action generation are insufficient for complex embodied tasks that require global planning, cross-stage state maintenance, execution verification, and failure recovery. We refer to this mismatch as the prediction-deliberation gap. To address this gap, we propose HarnessWAM, an agentic framework for WAMs. HarnessWAM employs a vision-language-model-based Task Manager to maintain an evidence-grounded scene belief and organize the global instruction into a structured task graph. Capability-conditioned executable-space projection then compiles the graph into WAM-supported skill sequences that satisfy task dependencies and embodiment-state constraints. During execution, HarnessWAM couples a lightweight progress estimator with event-triggered Task Manager deliberation. The estimator supplies frequent execution cues, while the Task Manager uses observations, task state, and interaction history to verify outcomes and decide whether to advance, acquire evidence, revise the plan, or recover. Local recovery preserves acquired scene knowledge so that execution can resume after failure. HarnessWAM achieves state-of-the-art average performance on RoboMemArena, with full-task and subtask success rates of 64.4% and 76.8%, respectively, and reaches 23.7% success on RoboCerebra Ideal. On a physical UR3 arm, full-task success reaches 95% for shape-conditioned tabletop tidying and 90% for memory-dependent box exploration. These results demonstrate the effectiveness of model-external agentic orchestration in bridging the prediction-deliberation gap for complex embodied tasks.

cs.RO↗

arXiv2026

VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings

Universal multimodal retrieval requires compact embeddings that preserve task-relevant semantic information across diverse modalities. Prior works have incorporated latent reasoning into multimodal embedding learning to refine this information before embedding extraction. However, most existing approaches remain confined to deterministic latent paths, without exploring alternative trajectories to discover better embeddings. Thus, we propose VaME (Variational Multimodal Embeddings), a framework that models latent reasoning as a learnable distribution over trajectories. Specifically, we first introduce Variational Latent Reasoning (VLR) to enable autoregressive exploration in latent space, guided by answer reconstruction through a lightweight decoder. Meanwhile, we augment the original embedding-token readout with a latent-fused embedding to facilitate exploration during subsequent reinforcement learning. Finally, we optimize latent reasoning over stochastic variational trajectories through reinforcement learning, using Semantic Decoding Reward (SDR) to favor semantically meaningful trajectories with interpretable decoded outcomes. On the 78-task MMEB-V2 benchmark, spanning image, video, and visual-document retrieval, VaME outperforms most explicit CoT-based models and all latent-reasoning baselines. VaME also demonstrates robust performance on reasoning-intensive benchmarks such as MRMR, with substantial gains after reinforcement learning. Importantly, VaME achieves these gains with at least a 4.25x inference speedup over the deterministic latent autoregressive baselines. The code will be made publicly available.

cs.CV↗

arXiv2026

PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle

Recent studies develop pixel-level multimodal large language models (MLLMs) that support both Region Segmentation and Region Understanding, extending multimodal interaction from whole images to specific objects and regions. However, these methods face two fundamental challenges. First, the scarcity of high-quality mask--text pairs leaves abundant mask annotations without corresponding language supervision. Second, discrepancies in supervision formats and learning-signal densities induce optimization interference between Region Segmentation and Region Understanding. To address these challenges, we propose PixVL, a self-supervised post-training framework that introduces a unified Mask--Text Consistency Cycle, enabling pixel-level MLLMs to generate and self-verify regional descriptions and learn from unlabeled data. We found that direct cycle based solely on geometric reconstruction is unreliable because re-segmentation IoU does not faithfully reflect the semantic quality and referring sufficiency. PixVL therefore introduces confuser-aware semantic verification, which uses the model's confidence when it correctly chooses the target among highly similar candidate regions, and assigns zero reward to an incorrect choice. Meanwhile, PixVL performs cross-view verification using temporally separated video frames or geometrically transformed image views, preventing cyclic learning from collapsing to positional and shape shortcuts. Finally, a quality-coupled bidirectional learning strategy uses the highest-reward description to guide Text-to-Mask learning. This strategy transforms Region Understanding and Region Segmentation from competing tasks into mutual generators and verifiers. Experiments demonstrate that PixVL improves both region understanding task and segmentation task.

cs.CV↗

arXiv2026

From killed BBM with drift to BBM: the extremal process

In this paper, we study the asymptotic behavior of the extremal process of a standard one-dimensional branching Brownian motion (BBM) with drift $-ρ>-\sqrt2$ and absorbing barrier at level $-x$. We prove that the two-dimensional point process, with first component being the extremal process of the BBM and the second component being the running minimum of the BBM with drift, converges weakly to a decorated Poisson point process (DPPP) on $\mathbb{R} \times [0, \infty)$. This framework allows us to supply a common limit coupling of the extremal processes for different barrier levels and to explicitly derive the limit, as $t\to\infty$, of the extremal process of the killed BBM killed at level $-x$, demonstrating that the double limit, when $t\to\infty$ first and then $x\to\infty$, of the extremal process of the BBM killed at level $-x$ coincides with the limit of the extremal process of (un-killed) BBM.

math.PR↗

arXiv2026

APEX: Active Protection at Execution Boundaries for LLM Agents

Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind them. We instead shift defense from covering attack patterns to one stable point: whatever the carrier and however the injection propagates, harm materializes only at the \emph{execution boundary}, where the agent turns internal state into an external action or released output. Safety there turns on two conditions, both settled by the trusted task rather than by the run: whether the proposed effect is authorized, and whether the runtime information reaching it is endorsed by that task. We present APEX, an active defense that enforces both at this boundary from a single authorization contract compiled before untrusted execution: \emph{evidence-gated prevention} admits an effect only when the contract justifies it, while \emph{deception-based exposure} makes unendorsed use reveal itself before the effect commits. Protection therefore follows from what the task permits rather than from how an attack is built, and applies uniformly across capability units without attack-specific policies or taint tracking. Against 13 baselines, APEX attains 0\% attack success on five of six benchmarks and 0.56\% on the sixth, holds 0\% under adaptive attacks on all three capability-unit types, and remains effective across defender backbones. Code is available at https://github.com/ZhengXR930/APEX_official/tree/official.

cs.CR↗

arXiv2026

Effective-Geometry Rescaling and Universal Critical Behavior in the Anisotropic Three-State Potts Model on the Square Lattice

We study the two-dimensional anisotropic three-state Potts ferromagnet on the square lattice using Wolff single-cluster Monte Carlo simulations and finite-size scaling. For coupling ratios $λ=J_y/J_x=0.5$, $0.75$, and $1$, finite-size scaling of the correlation ratio yields critical behavior consistent with the two-dimensional three-state Potts universality class. The scaling of the leading Fisher zeros gives a correlation-length exponent consistent with $ν=5/6$, while their cumulative density is consistent with the expected specific-heat exponent $α=1/3$. We further characterize the anisotropy at criticality using directional correlation ratios $R_x$ and $R_y$ together with directional FK wrapping probabilities. For $λ=0.5$ on a physically square lattice, $R_x$ and $R_y$ approach distinct critical values while yielding a common correlation-length exponent. From the wrapping probabilities, we independently determine an effective aspect ratio $ρ_e^\square=0.6413(5)$, in close agreement with the theoretical value $ρ_e^{\square,\mathrm{th}}\simeq0.64150030$ obtained from the isoradial representation. Using the theoretical value to set the physical aspect ratio restores directional equivalence, $R_x\simeq R_y$, and brings the overall correlation ratio toward the isotropic-square reference. The results show that spatial anisotropy changes the effective critical geometry without altering the bulk three-state Potts universality class.

cond-mat.stat-mech↗