arXiv subjects

Eric Wang

Publications and source records attributed to Eric Wang.

At least 19 recordsLinked to original sources

arXiv2026

Pre-shipment optical characterization of the SCALES instrument

The Slicer Combined with an Array of Lenslets for Exoplanet Spectroscopy (SCALES) instrument is a 1-5 micron imager and 2-5 micron integral field spectrograph, currently being commissioned on the Keck II Telescope. SCALES is optimized for exoplanet high-contrast imaging and spectroscopic characterization, and will be sensitive to older, colder exoplanets than existing instrumentation. The 12.3" x 12.3" imaging channel is designed to replicate the capabilities of NIRC2, and the low (R~35-200, 2.2" x 2.2" FOV) and medium (R~2500-5000, 0.36" x 0.34" FOV) spectral resolution modes offer new capabilities compared to existing Keck instrumentation. We present preliminary optical performance results from laboratory testing and commissioning of SCALES.

astro-ph.IM↗

arXiv2026

Measuring the Re-executability of Published Molecular Docking Claims

Published molecular docking scores depend on the receptor, ligand, software, search box, seed, and preparation choices; a paper reporting only the score has published a number with unknowable provenance. We ask whether such claims can be re-executed from their own published records. We introduce MERS-Dock, a 16-field Minimum Executable Reporting Set, and a deterministic E0-E4 executability ladder over audited field states. In 236 open-access SARS-CoV-2 main-protease docking papers, only 8.1% met the essential-field rule for direct re-execution (E3), 47.9% were blocked by a missing foundational field (E1), and none reached E4; mean field completeness was 49.1% and the search-box centre was reported by only 33.9%. We validated the audit against two independent human reviewers on a 65-paper stratified sample: inter-reviewer agreement was 92% (pooled Cohen kappa 0.87), and the automated agent matched humans on the execution-blocking fields while over-calling two non-blocking fields; the resulting E-class was 68% concordant with humans and, where it differed, human review lowered the executable count -- so the low-executability finding is confirmed, not inflated. Reporting did not improve over 2021-2026 (completeness vs year Spearman rho = -0.01). A bounded within-paper re-execution shows the reproduction gap is a box-coverage geometry effect, not box-size disclosure. We read E-class as an executability gate, not a reproducibility predictor, and release Mpro-DockExec as a traceable measurement layer for digital-library and evidence-synthesis systems deciding what is checkable in published computational claims.

cs.DL↗

arXiv2026

On the Assadi Liu Tarjan Auction Algorithm for Bipartite Matching: Simplification, Alternative Analysis, and Hard Instance

Assadi, Liu, and Tarjan [SOSA'21] gave an auction algorithm that outputs a $(1-\epsilon)$-approximation to Maximum Matching in bipartite graphs. Their algorithm computes a sequence of $O(\frac{1}{\epsilon^2})$ maximal matchings in subgraphs of the input graph and can be implemented in the multi-pass streaming setting with $O(\frac{1}{\epsilon^2})$ passes in a straightforward manner, which constitutes the state-of-the-art pass/approximation trade-off result in the multi-pass streaming setting. Their analysis uses tools from combinatorial auctions and, at its heart, relies on a clever potential function argument. Their proof, however, provides only limited insight into the inner workings of the algorithm. In this paper, we revisit the ALT-algorithm and present the following contributions. Simplification: The ALT-algorithm is built upon a freezing mechanism where vertices on one side of the bipartition that have already been rematched $\Theta(\frac{1}{\epsilon})$ times over the course of the algorithm remain matched to their current partner forever. We show that this mechanism is in fact unnecessary, i.e., no special treatment of such vertices is needed. Alternative Analysis: We give an alternative analysis of the algorithm that is based on augmenting paths. Our analysis allows for a reinterpretation as one that follows the traditional approach of searching for and eliminating augmenting paths. Our analysis also copes with the removal of the freezing mechanism in a natural way, whereas the analysis of Assadi et al. strictly depends on its use. Hard Instance: We provide the first hard instance on which the algorithm requires $\Omega(\frac{1}{\epsilon^2})$ iterations/maximal matching computations. The instance is a simple path graph, where we exhibit a cyclic behaviour that prevents fast progress.

cs.DS↗

arXiv2026

How Post-Training Shapes Biological Reasoning Models

Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood. We study when post-training improves performance and when it induces over-specialization. Across genomics, transcriptomics, and proteins, we train and evaluate more than 100 biological reasoning models under controlled variation in backbone, continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL), measuring both in-domain (ID) and out-of-domain (OOD) performance. We find that each post-training stage reshapes generalization in a distinct way rather than contributing uniform gains. CPT improves downstream performance by aligning models with biological language. SFT consistently increases ID performance but causes OOD performance to peak early and decline as models fit the training distribution. RL, when applied to strong SFT checkpoints with aligned rewards, improves OOD performance and partially recovers generalization. These results show that biological reasoning does not improve monotonically with additional supervision or compute. Instead, performance depends on how training stages are composed. Under fixed post-training budgets, the strongest ID-OOD trade-off comes from brief SFT, larger RL allocations, and asymmetric adaptation capacity across stages.

cs.LG↗

arXiv2026

A Backward Ergodic Theorem for Uncountable-to-one Transformations

We establish a generalization of Anush Tserunyan and Jenna Zomback's 2024 Backward Ergodic Theorem. We remove the countable-to-one assumption and thus provide a backward ergodic theorem for arbitrary measure-preserving transformations. However, this new setting introduces measurability concerns as unlike the countable-to-one case, we no longer have a collection of Borel right inverses. Instead, we must rely on the Jankov, von Neumann uniformization theorem. Towards this, we use Borel and measured field structures introduced by Stefaan Vaes and Lise Wouters.

math.DS↗

arXiv2026

MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences

Research agents have recently achieved significant progress in information seeking and synthesis across heterogeneous textual and visual sources. In this paper, we introduce MuSEAgent, a multimodal reasoning agent that enhances decision-making by extending the capabilities of research agents to discover and leverage stateful experiences. Rather than relying on trajectory-level retrieval, we propose a stateful experience learning paradigm that abstracts interaction data into atomic decision experiences through hindsight reasoning. These experiences are organized into a quality-filtered experience bank that supports policy-driven experience retrieval at inference time. Specifically, MuSEAgent enables adaptive experience exploitation through complementary wide- and deep-search strategies, allowing the agent to dynamically retrieve multimodal guidance across diverse compositional semantic viewpoints. Extensive experiments demonstrate that MuSEAgent consistently outperforms strong trajectory-level experience retrieval baselines on both fine-grained visual perception and complex multimodal reasoning tasks. These results validate the effectiveness of stateful experience modeling in improving multimodal agent reasoning.

cs.CV↗

arXiv2026

PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs

Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We present PAVE (Premise-Grounded Answer Validation and Editing), an inference-time validation layer for evidence-grounded question answering. PAVE decomposes retrieved context into question-conditioned atomic facts, drafts an answer, scores how well that draft is supported by the extracted premises, and revises low-support outputs before finalization. The resulting trace makes answer commitment auditable at the level of explicit premises, support scores, and revision decisions. In controlled ablations with a fixed retriever and backbone, PAVE outperforms simpler post-retrieval baselines in two evidence-grounded QA settings, with the largest gain reaching 32.7 accuracy points on a span-grounded benchmark. We view these findings as proof-of-concept evidence that explicit premise extraction plus support-gated revision can strengthen evidence-grounded consistency in retrieval-augmented LLM systems.

cs.CL↗

arXiv2026

TensorCommitments: A Lightweight Verifiable Inference for Language Models

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM inference, where a prover (the service) must convince a verifier (the client) that an inference was run correctly without rerunning the LLM. Existing cryptographic works are too slow at the LLM scale, while non-cryptographic ones require a strong verifier GPU. We propose TensorCommitments (TCs), a tensor-native proof-of-inference scheme. TC binds the LLM inference to a commitment, an irreversible tag that breaks under tampering, organized in our multivariate Terkle Trees. For LLaMA2, TC adds only 0.97% prover and 0.12% verifier time over inference while improving robustness to tailored LLM attacks by up to 48% over the best prior work requiring a verifier GPU.

cs.CR↗

arXiv2025

Competitively Constructed Planar Graphs

We introduce and study two Maker-Breaker-like games for constructing planar graphs: the edge drawing game, where two players take turns drawing non-intersecting edges between points in the plane, and the circle packing game, where the players take turns placing disjoint circles in the plane. Both games produce planar graphs: the edge drawing game results in a plane graph drawing, and the circle packing game yields a planar graph via the contact graph of the packing. For both games, we give necessary conditions under which a given planar graph can be constructed. We also show that the two games are indeed different by giving a class of graphs which can be constructed in one but not the other.

math.CO↗

arXiv2025

Gradient-based search of quantum phases: discovering unconventional fractional Chern insulators

The discovery and understanding of new quantum phases has time and again transformed both fundamental physics and technology, yet progress often relies on slow, intuition-based theoretical considerations or experimental serendipity. Here, we introduce a general gradient-based framework for targeted phase discovery. We define a differentiable function, dubbed "target-phase loss function", which encodes fingerprints of a quantum state, thereby recasting phase search as a tractable optimization problem in Hamiltonian space. The method is broadly applicable to a wide range of symmetry-broken and topological orders and can be interfaced with most many-body numerical solvers. As a demonstration, we apply it to spinless fermions on the kagome lattice using exact diagonalization and discover two distinctive fractional Chern insulators (FCIs): (i) at filling $\nu = 1/3$, a "non-ideal" Abelian FCI whose band geometry lies far beyond the Landau-level mimicry paradigm and all recent generalizations; and (ii) at $\nu = 1/2$, a non-Abelian FCI stabilized purely by finite-range two-body interactions. These results provide the first explicit realization of such types of FCIs and establish a versatile paradigm for systematic quantum-phase discovery.

cond-mat.str-el↗

arXiv2025

Laboratory testing and characterization of a hybrid fast/slow readout mode for the H2RG detectors in SCALES

The upcoming SCALES (Slicer Combined with Array of Lenslets for Exoplanet Spectroscopy) instrument for W.M. Keck Observatory will enable new imaging and low-/mid-resolution coronagraphic integral field spectroscopic observations over the wavelength range from 2-5 microns. At the heart of the instrument are two HgCdTe Teledyne Imaging H2RG detectors, designed for a 100kHz pixel clock rate (slow mode) with a fixed 4-channel readout. However, in ground-based operation at these wavelengths, the resulting minimum frame readout time will result in the infrared background saturating the detector. To enable high quality observations without saturation from the bright infrared sky background, we operate the detectors using a custom cable for buffered readout via the Teledyne Imaging SIDECAR ASIC followed by an AstroBlank/Markury Scientific MACIE controller card controlled by custom firmware. This combination allows the detector to be read out at faster pixel clock rates. This, in combination with the slow-mode H2RG, is what we characterize as hybrid fast-slow readout, enabling readout up to 18 times faster than would be possible in slow mode alone. In the UCLA Infrared Lab, we have performed room-temperature and cold tests with the H2RG detectors. We test and optimize full-frame data acquisition with pixel clock rates from 0.2-1.8 MHz. In these proceedings, we present a summary of the controller software used to operate the H2RG-ASIC-MACIE system. We present the methodology of, and preliminary results from, the UCLA tests of cryogenic operation of both H2RG detectors. We also outline the next steps in verification of detector performance, as well as integration with the SCALES instrument.

astro-ph.IM↗

arXiv2025

An analytical framework for the Levine hats problem: new strategies, bounds and generalizations

We study the Levine hat problem, a cooperative puzzle introduced by Lionel Levine in 2010, in which $n \geq 2$ players must simultaneously identify a black hat on their own infinite stack, each seeing only their teammates' stacks. While the optimal winning probability $V_n$ remains unknown even for $n=2$, we make three key advances. First, we develop a geometric and integral framework representing strategies as Lebesgue-measurable functions, yielding a new integral expression for $V_n$ and a unified treatment of finite and infinite stacks. Second, we construct a recursive strategy $\mathscr{S}_5$ processing hats in blocks of five, which attains the conjectured optimal probability $7/20$ for two players. Although this bound was already achieved by the known strategy $\mathscr{S}_3$, the existence of $\mathscr{S}_5$ refutes the previously held expectation that recursive strategies with block size greater than three yield no improvement, and produces a strictly better geometric convergence rate for $V_{2,h}$ as well as a new lower bound for $V_2(p)$ which improves known results for $p < 0.312$. Building upon this, we improve the geometric convergence rate of $V_{2,h}$ up to the near-optimal $1/4^{1-\varepsilon}$ for any $\varepsilon > 0$. Third, we introduce and completely solve a generalization of the problem where players are given uncountably infinite stacks of hats, showing that the optimal winning probability in this setting equals exactly $1/2$ for all $n \geq 2$. This new formulation allows to study the original combinatorial problem using tools from analytic optimization, and provides a natural framework for computing optimal responses to fixed strategies.

math.CO↗

arXiv2025

Multi-Agent Path Finding Among Dynamic Uncontrollable Agents with Statistical Safety Guarantees

Existing multi-agent path finding (MAPF) solvers do not account for uncertain behavior of uncontrollable agents. We present a novel variant of Enhanced Conflict-Based Search (ECBS), for both one-shot and lifelong MAPF in dynamic environments with uncontrollable agents. Our method consists of (1) training a learned predictor for the movement of uncontrollable agents, (2) quantifying the prediction error using conformal prediction (CP), a tool for statistical uncertainty quantification, and (3) integrating these uncertainty intervals into our modified ECBS solver. Our method can account for uncertain agent behavior, comes with statistical guarantees on collision-free paths for one-shot missions, and scales to lifelong missions with a receding horizon sequence of one-shot instances. We run our algorithm, CP-Solver, across warehouse and game maps, with competitive throughput and reduced collisions.

cs.MA↗

arXiv2025

Apple Intelligence Foundation Language Models: Tech Report 2025

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

cs.LG↗

arXiv2025

Mercury: Ultra-Fast Language Models Based on Diffusion

We present Mercury, a new generation of commercial-scale large language models (LLMs) based on diffusion. These models are parameterized via the Transformer architecture and trained to predict multiple tokens in parallel. In this report, we detail Mercury Coder, our first set of diffusion LLMs designed for coding applications. Currently, Mercury Coder comes in two sizes: Mini and Small. These models set a new state-of-the-art on the speed-quality frontier. Based on independent evaluations conducted by Artificial Analysis, Mercury Coder Mini and Mercury Coder Small achieve state-of-the-art throughputs of 1109 tokens/sec and 737 tokens/sec, respectively, on NVIDIA H100 GPUs and outperform speed-optimized frontier models by up to 10x on average while maintaining comparable quality. We discuss additional results on a variety of code benchmarks spanning multiple languages and use-cases as well as real-world validation by developers on Copilot Arena, where the model currently ranks second on quality and is the fastest model overall. We also release a public API at https://platform.inceptionlabs.ai/ and free playground at https://chat.inceptionlabs.ai

cs.CL↗

arXiv2025

Unfolding Boxes with Local Constraints

We consider the problem of finding and enumerating polyominos that can be folded into multiple non-isomorphic boxes. While several computational approaches have been proposed, including SAT, randomized algorithms, and decision diagrams, none has been able to perform at scale. We argue that existing SAT encodings are hindered by the presence of global constraints (e.g., graph connectivity or acyclicity), which are generally hard to encode effectively and hard for solvers to reason about. In this work, we propose a new SAT-based approach that replaces these global constraints with simple local constraints that have substantially better propagation properties. Our approach dramatically improves the scalability of both computing and enumerating common box unfoldings: (i) while previous approaches could only find common unfoldings of two boxes up to area 88, ours easily scales beyond 150, and (ii) while previous approaches were only able to enumerate common unfoldings up to area 30, ours scales up to 60. This allows us to rule out 46, 54, and 58 as the smallest areas allowing a common unfolding of three boxes, thereby refuting a conjecture of Xu et al. (2017).

cs.CG↗

arXiv2025

CAST: Time-Varying Treatment Effects with Application to Chemotherapy and Radiotherapy on Head and Neck Squamous Cell Carcinoma

Causal machine learning (CML) enables individualized estimation of treatment effects, offering critical advantages over traditional correlation-based methods. However, existing approaches for medical survival data with censoring such as causal survival forests estimate effects at fixed time points, limiting their ability to capture dynamic changes over time. We introduce Causal Analysis for Survival Trajectories (CAST), a novel framework that models treatment effects as continuous functions of time following treatment. By combining parametric and non-parametric methods, CAST overcomes the limitations of discrete time-point analysis to estimate continuous effect trajectories. Using the RADCURE dataset [1] of 2,651 patients with head and neck squamous cell carcinoma (HNSCC) as a clinically relevant example, CAST models how chemotherapy and radiotherapy effects evolve over time at the population and individual levels. By capturing the temporal dynamics of treatment response, CAST reveals how treatment effects rise, peak, and decline over the follow-up period, helping clinicians determine when and for whom treatment benefits are maximized. This framework advances the application of CML to personalized care in HNSCC and other life-threatening medical conditions. Source code/data available at: https://github.com/CAST-FW/HNSCC

cs.LG↗

arXiv2025

TxGemma: Efficient and Agentic LLMs for Therapeutics

Therapeutic development is a costly and high-risk endeavor that is often plagued by high failure rates. To address this, we introduce TxGemma, a suite of efficient, generalist large language models (LLMs) capable of therapeutic property prediction as well as interactive reasoning and explainability. Unlike task-specific models, TxGemma synthesizes information from diverse sources, enabling broad application across the therapeutic development pipeline. The suite includes 2B, 9B, and 27B parameter models, fine-tuned from Gemma-2 on a comprehensive dataset of small molecules, proteins, nucleic acids, diseases, and cell lines. Across 66 therapeutic development tasks, TxGemma achieved superior or comparable performance to the state-of-the-art generalist model on 64 (superior on 45), and against state-of-the-art specialist models on 50 (superior on 26). Fine-tuning TxGemma models on therapeutic downstream tasks, such as clinical trial adverse event prediction, requires less training data than fine-tuning base LLMs, making TxGemma suitable for data-limited applications. Beyond these predictive capabilities, TxGemma features conversational models that bridge the gap between general LLMs and specialized property predictors. These allow scientists to interact in natural language, provide mechanistic reasoning for predictions based on molecular structure, and engage in scientific discussions. Building on this, we further introduce Agentic-Tx, a generalist therapeutic agentic system powered by Gemini 2.5 that reasons, acts, manages diverse workflows, and acquires external domain knowledge. Agentic-Tx surpasses prior leading models on the Humanity's Last Exam benchmark (Chemistry & Biology) with 52.3% relative improvement over o3-mini (high) and 26.7% over o3-mini (high) on GPQA (Chemistry) and excels with improvements of 6.3% (ChemBench-Preference) and 2.4% (ChemBench-Mini) over o3-mini (high).

cs.AI↗