arXiv subjects

Karan Singh

Publications and source records attributed to Karan Singh.

At least 19 recordsLinked to original sources

arXiv2026

Learning to Price with Persuasion

Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves information and mechanism design. Specifically, we consider the economic setting recently introduced by Bergemann et al. (2022), where in addition to the menu of quality-price pairs, the seller offers information on the value of the match between product quality and buyer's taste via a signaling scheme. We relax the assumption that the seller knows the buyers' belief about the distribution of tastes and study the sample requirements of designing a revenue maximizing scheme. We consider both the batch setting where we have access to data from a set of i.i.d. buyers and an online demand query model where we observe the buyers' behaviors to seller's schemes. Despite the apparent non-convexity of the problem, we also give the first FPTAS to compute a scheme that maximizes the revenue within an arbitrarily small additive loss, which was left open by Bergemann et al. (2022). Overall, this brings a new learning perspective in asymmetric economic settings where buyers and sellers know different types of information.

cs.GT↗

arXiv2026

TokTalk: Expressive Real-time Facial Animation from Audio-LLM Tokens

Recent advances in Audio-LLMs like GPT-4o have ushered in an era of conversational interaction with language models. Conversational avatars however, still seem robotic in facial expression and conversational flow, in part due to sequential stages of speech recognition, text generation, turn-based text response, speech synthesis, and audio driven facial animation. Based on our insight that audio-tokens produced by current Audio-LLMs carry sufficient information to reconstruct a plausible facial performance, we present TokTalk, a system that directly outputs expressive facial animation in real-time from streaming audio-tokens. We construct a novel audio-token to 3D facial motion dataset, on which TokTalk is trained using a Chunk-based Conditional Flow Matching model. A lightweight adaptation strategy allows our trained model to seamlessly connect to any token-based Audio-LLM at minimal computational overhead. Our chunk-based processing further enables parametric trade-off between latency and facial quality, shown through ablation studies. We further show that the real-time performance of TokTalk is comparable in latency to prior art solutions, and significantly favorable (via a perceptual study) in terms of quality, expressivity and control of the 3D facial performance. We showcase TokTalk's flexibility using a chatbot Avatar, a voice-driven user Avatar, and an animation Director's interface, as diverse audio-visual face applications.

cs.CV↗

arXiv2026

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models

Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization, question answering, retrieval-augmented generation, and agentic interaction. This fragmentation makes it unclear whether a mitigation that works in one setting reduces hallucinations across contexts. Current benchmarks either require human annotation and fixed references that may be memorized, or rely on observations in settings that are difficult to reproduce. To study root causes, we introduce HalluWorld, an extensible benchmark grounded in an explicit reference-world formulation: a model hallucinates when it produces an observable claim that is false with respect to this world. Building on this view, we construct synthetic and semi-synthetic environments in which the reference world is fully specified, the model's view is controlled, and hallucination labels are generated automatically. HalluWorld spans gridworlds, chess, and realistic terminal tasks, enabling controlled variation of world complexity, observability, temporal change, and source-conflict policy, and disentangling hallucinations into fine-grained error categories. We evaluate frontier and open-weight language models across these settings and find consistent patterns: perceptual hallucination on directly observed information is near-solved for frontier models, while multi-step state tracking and causal forward simulation remain difficult and are not generally solved by extended thinking. In the terminal setting, models also struggle with when to abstain. The uneven profile of failures across probe types and domains suggests that hallucinations arise from distinct failure modes rather than a single capability. Our results suggest that controlled reference worlds offer a scalable and reproducible path toward measuring and reducing hallucinations in modern language models.

cs.CL↗

arXiv2026

Replicable Bandits with UCB based Exploration

We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration. A bandit algorithm is $\rho$-replicable if two executions using shared internal randomness but independent reward realizations produce the same action sequence with probability at least $1-\rho$. Prior approaches to this problem are elimination-based and, in linear bandits with infinitely many actions, rely on discretization, leading to suboptimal dependence on the dimension $d$ and $\rho$. We develop optimistic alternatives for both settings. For stochastic multi-armed bandits, we propose RepUCB, a replicable batched UCB algorithm and show that it attains a regret $O\!\left(\frac{K^2\log^2 T}{\rho^2}\sum_{a:\Delta_a>0}\left(\Delta_a+\frac{\log(KT\log T)}{\Delta_a}\right)\right)$. For stochastic linear bandits, we first introduce RepRidge, a replicable ridge regression estimator that satisfies both a confidence guarantee and a $\rho$-replicability guarantee. Beyond its role in our bandit algorithm, this may also be of independent interest in other statistical estimation settings. We then use RepRidge to design RepLinUCB, a replicable optimistic algorithm for stochastic linear bandits, and show that its regret is bounded by $\widetilde{O}\!\big(\big(d+\frac{d^3}{\rho}\big)\sqrt{T}\big)$. This improves the best prior regret guarantee by a factor of $O(d/\rho)$, showing that our optimistic algorithm can substantially reduce the price of replicability. This is the first linear-bandit algorithm with an optimal dependence on $\rho$ for large number of arms. Finally, we extend our framework to stochastic generalized linear bandits by developing RepGLM, a replicable penalized GLM estimator, and RepGLMUCB, a replicable optimistic algorithm for this setting.

cs.LG↗

arXiv2026

To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. In this work, we systematically study the trade-off between pretraining and retrieval by training OLMo-2-based LMs ranging from 30M to 3B parameters on up to 100B DCLM tokens, while varying pretraining data scale, retrieval store size, and retrieval store source (pretraining vs. new data) across reasoning, scientific QA, and open-domain QA benchmarks. We find that retrieval gains depend on model capacity and pretraining exposure and are strongly front-loaded, with a median 91% of the largest observed improvement realized by one retrieval token per model parameter. However, the interaction is objective-dependent: smaller models gain more in gold-answer perplexity, whereas larger, more-pretrained models gain more in accuracy. Retrieval from previously seen data also preserves most of the held-out retrieval gain. Retrieval is therefore a task-, regime-, and metric-dependent complement to parametric learning whose value also depends on datastore size and information novelty. Overall, this motivates the explicit partitioning of data between internalization and external access for LM design.

cs.CL↗

arXiv2026

Unusual magnetic and charge transport properties in In-Substituted Half-Metallic Kagome Ferromagnet Co3Sn2S2

The kagome ferromagnet Co3Sn2S2 has been studied extensively for its unusual topology of electronic bands, origin of ferromagnetism and strong coupling between magnetism and charge transport. To understand the role of nonmagnetic element Sn, we have investigated magnetic, transport, and electronic structure of the isostructural compound Co3SnInS2, where all the Sn (divalent) atoms in the Co3Sn Kagome layer are replaced by In (trivalent) atoms. We find long-range ferromagnetic order is nearly quenched in Co3SnInS2. The system exhibits predominantly antiferromagnetic correlations with only a very small net magnetic moment and turns ferromagnetic in the presence of an external magnetic field. Transport measurements show a semiconducting behaviour at low temperatures. Magnetoresistance shows a nonmonotonic field dependence, changing from negative to positive with increasing magnetic field. An anomalous Hall effect is observed, but its magnitude is significantly reduced compared to Co3Sn2S2 where the topological character of the Fermi surface plays a dominant role. These results indicate that substitution of Sn by In in the Co3Sn plane not only suppresses the topological electronic features of the transport electrons but drives the system away from the ferromagnetic Half-metallicity to an almost nonmagnetic semiconducting state with unusual paramagnetic response. Electronic structure calculations are consistent with some of these observations.

cond-mat.mtrl-sci↗

arXiv2026

Inverse Optimization Without Inverse Optimization: Direct Solution Prediction with Transformer Models

We present an end-to-end framework for generating solutions to combinatorial optimization problems with unknown components using transformer-based sequence-to-sequence neural networks. Our framework learns directly from past solutions and incorporates the known components, such as hard constraints, via a constraint reasoning module, yielding a constrained learning scheme. The trained model generates new solutions that are structurally similar to past solutions and are guaranteed to respect the known constraints. We apply our approach to three combinatorial optimization problems with unknown components: the knapsack problem with an unknown reward function, the bipartite matching problem with an unknown objective function, and the single-machine scheduling problem with release times and unknown precedence constraints, with the objective of minimizing average completion time. We demonstrate that transformer models have remarkably strong performance and often produce near-optimal solutions in a fraction of a second. They can be particularly effective in the presence of more complex underlying objective functions and unknown implicit constraints compared to an LSTM-based alternative and inverse optimization.

math.OC↗

arXiv2026

Learning to Build Shapes by Extrusion

We introduce Text Encoded Extrusions (TEE), a text-based representation that expresses mesh construction as sequences of face extrusions rather than polygon lists, and a method for generating 3D meshes from TEE using a large language model (LLM). By learning extrusion sequences that assemble a mesh, similar to the way artists create meshes, our approach naturally supports arbitrary output face counts and produces manifold meshes by design, in contrast to recent mesh generative transformer based models. The learnt extrusion sequences can also be applied to existing meshes - enabling editing in addition to generation. To train our model, we decompose a library of quadrilateral meshes with non-self-intersecting face loops into constituent loops, which can be viewed as their building blocks, and finetune an LLM on the steps for reassembling the quadrilateral meshes by performing a sequence of extrusions. We demonstrate that our representation enables reconstruction, novel shape synthesis, and the addition of new features to existing meshes.

cs.GR↗

arXiv2025

A Unified Definition of Hallucination: It's The World Model, Stupid!

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we also connect our framework to HalluWorld, a complementary benchmark that instantiates fully specified reference world models for stress-testing model hallucinations.

cs.CL↗

arXiv2025

How to Sell High-Dimensional Data Optimally

Motivated by the problem of selling large, proprietary data, we consider an information pricing problem proposed by Bergemann et al. that involves a decision-making buyer and a monopolistic seller. The seller has access to the underlying state of the world that determines the utility of the various actions the buyer may take. Since the buyer gains greater utility through better decisions resulting from more accurate assessments of the state, the seller can therefore promise the buyer supplemental information at a price. To contend with the fact that the seller may not be perfectly informed about the buyer's private preferences (or utility), we frame the problem of designing a data product as one where the seller designs a revenue-maximizing menu of statistical experiments. Prior work by Cai et al. showed that an optimal menu can be found in time polynomial in the state space, whereas we observe that the state space is naturally exponential in the dimension of the data. We propose an algorithm which, given only sampling access to the state space, provably generates a near-optimal menu with a number of samples independent of the state space. We then analyze a special case of high-dimensional Gaussian data, showing that (a) it suffices to consider scalar Gaussian experiments, (b) the optimal menu of such experiments can be found efficiently via a semidefinite program, and (c) full surplus extraction occurs if and only if a natural separation condition holds on the set of potential preferences of the buyer.

cs.GT↗

arXiv2025

Mesh Processing Non-Meshes via Neural Displacement Fields

Mesh processing pipelines are mature, but adapting them to newer non-mesh surface representations -- which enable fast rendering with compact file size -- requires costly meshing or transmitting bulky meshes, negating their core benefits for streaming applications. We present a compact neural field that enables common geometry processing tasks across diverse surface representations. Given an input surface, our method learns a neural map from its coarse mesh approximation to the surface. The full representation totals only a few hundred kilobytes, making it ideal for lightweight transmission. Our method enables fast extraction of manifold and Delaunay meshes for intrinsic shape analysis, and compresses scalar fields for efficient delivery of costly precomputed results. Experiments and applications show that our fast, compact, and accurate approach opens up new possibilities for interactive geometry processing.

cs.GR↗

arXiv2025

Nature of field-induced transitions and hysteretic magnetoresistance in non-collinear antiferromagnet EuIn2As2

We examine the magnetic and electrical transport properties of the hexagonal EuIn2As2 compound, combining experimental and theoretical results. This compound is predicted to be an axion-insulator from an electronic point of view and an altermagnet while in the collinear magnetic phase. However, experiments indicate that the Fermi level lies within the valence band rather than in the topological gap, potentially leading to the dominance of magnetic properties. Our detailed studies on magnetization and electrical transport support the presence of a broken-helix antiferromagnetic state, which was previously identified by X-ray and neutron diffraction experiments. Notably, we observed within that state a field-induced metamagnetic transition marked by a large hysteresis in magnetoresistance, which turns into a sharp upturn for the magnetic field tilted by 15 degree from the c-axis of the crystal. Combined with theoretical calculations, it is explained that the application of a magnetic field changes the low-resistivity antiferromagnetic domain walls to the high-resistivity domain walls due to the reduction in the Fermi surface sheets interaction area in the domain walls, originating from p-orbitals of As. EuIn2As2, therefore, presents a new case study that broadens the understanding of complex magnetic structures and their influence on electrical transport.

cond-mat.mtrl-sci↗

arXiv2025

Model See Model Do: Speech-Driven Facial Animation with Style Control

Speech-driven 3D facial animation plays a key role in applications such as virtual avatars, gaming, and digital content creation. While existing methods have made significant progress in achieving accurate lip synchronization and generating basic emotional expressions, they often struggle to capture and effectively transfer nuanced performance styles. We propose a novel example-based generation framework that conditions a latent diffusion model on a reference style clip to produce highly expressive and temporally coherent facial animations. To address the challenge of accurately adhering to the style reference, we introduce a novel conditioning mechanism called style basis, which extracts key poses from the reference and additively guides the diffusion generation process to fit the style without compromising lip synchronization quality. This approach enables the model to capture subtle stylistic cues while ensuring that the generated animations align closely with the input speech. Extensive qualitative, quantitative, and perceptual evaluations demonstrate the effectiveness of our method in faithfully reproducing the desired style while achieving superior lip synchronization across various speech scenarios.

cs.GR↗

arXiv2025

Sample-Optimal Agnostic Boosting with Unlabeled Data

Boosting provides a practical and provably effective framework for constructing accurate learning algorithms from inaccurate rules of thumb. It extends the promise of sample-efficient learning to settings where direct Empirical Risk Minimization (ERM) may not be implementable efficiently. In the realizable setting, boosting is known to offer this computational reprieve without compromising on sample efficiency. However, in the agnostic case, existing boosting algorithms fall short of achieving the optimal sample complexity. This paper highlights an unexpected and previously unexplored avenue of improvement: unlabeled samples. We design a computationally efficient agnostic boosting algorithm that matches the sample complexity of ERM, given polynomially many additional unlabeled samples. In fact, we show that the total number of samples needed, unlabeled and labeled inclusive, is never more than that for the best known agnostic boosting algorithm -- so this result is never worse -- while only a vanishing fraction of these need to be labeled for the algorithm to succeed. This is particularly fortuitous for learning-theoretic applications of agnostic boosting, which often take place in the distribution-specific setting, where unlabeled samples can be availed for free. We detail other applications of this result in reinforcement learning.

cs.LG↗

arXiv2025

Faster Global Minimum Cut with Predictions

Global minimum cut is a fundamental combinatorial optimization problem with wide-ranging applications. Often in practice, these problems are solved repeatedly on families of similar or related instances. However, the de facto algorithmic approach is to solve each instance of the problem from scratch discarding information from prior instances. In this paper, we consider how predictions informed by prior instances can be used to warm-start practical minimum cut algorithms. The paper considers the widely used Karger's algorithm and its counterpart, the Karger-Stein algorithm. Given good predictions, we show these algorithms become near-linear time and have robust performance to erroneous predictions. Both of these algorithms are randomized edge-contraction algorithms. Our natural idea is to probabilistically prioritize the contraction of edges that are unlikely to be in the minimum cut.

cs.DS↗

arXiv2024

Motion Modes: What Could Happen Next?

Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific motions from motion arrow input, they rely on synthetic data and predefined motions, limiting their application to complex scenes. We introduce Motion Modes, a training-free approach that explores a pre-trained image-to-video generator's latent distribution to discover various distinct and plausible motions focused on selected objects in static images. We achieve this by employing a flow generator guided by energy functions designed to disentangle object and camera motion. Additionally, we use an energy inspired by particle guidance to diversify the generated motions, without requiring explicit training data. Experimental results demonstrate that Motion Modes generates realistic and varied object animations, surpassing previous methods and even human predictions regarding plausibility and diversity. Project Webpage: https://motionmodes.github.io/

cs.CV↗

arXiv2024

Sample-Efficient Agnostic Boosting

The theory of boosting provides a computational framework for aggregating approximate weak learning algorithms, which perform marginally better than a random predictor, into an accurate strong learner. In the realizable case, the success of the boosting approach is underscored by a remarkable fact that the resultant sample complexity matches that of a computationally demanding alternative, namely Empirical Risk Minimization (ERM). This in particular implies that the realizable boosting methodology has the potential to offer computational relief without compromising on sample efficiency. Despite recent progress, in agnostic boosting, where assumptions on the conditional distribution of labels given feature descriptions are absent, ERM outstrips the agnostic boosting methodology in being quadratically more sample efficient than all known agnostic boosting algorithms. In this paper, we make progress on closing this gap, and give a substantially more sample efficient agnostic boosting algorithm than those known, without compromising on the computational (or oracle) complexity. A key feature of our algorithm is that it leverages the ability to reuse samples across multiple rounds of boosting, while guaranteeing a generalization error strictly better than those obtained by blackbox applications of uniform convergence arguments. We also apply our approach to other previously studied learning problems, including boosting for reinforcement learning, and demonstrate improved results.

cs.LG↗

arXiv2024

Evidence of variable range hopping in the Zintl phase EuIn2P2

We report a comprehensive characterization of the magnetic, electrical transport, spectral, and thermal properties of single-crystalline Zintl-type material EuIn2P2. The compound crystallizes with a hexagonal unit cell (space group P63/mmc) and orders magnetically at TC=24K with the Eu magnetic moments aligned ferromagnetically within the ab plane but tilted alternately along the c-axis direction. The effective and saturation magnetic moments agree with the theoretical values expected for the Eu2+ ion. For a range of several tens of kelvins above 40K, the electrical transport of EuIn2P2 is dominated by short-range magnetic interactions. The temperature dependence of the electrical resistivity has been modelled in terms of variable-range hopping. Another indication of the latter scenario seems to be the observation for EuIn2P2 of a quadratic dependence of the negative magnetoresistance on the magnetic field strength and the scaled magnetization. The temperature dependence of Raman band position and FWHM, as well as phonon lifetime, confirms the presence of the distinctive regions observed in transport and magnetic studies.

cond-mat.mtrl-sci↗