TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields2414Multimodal513AI agents455Frontier LLMs312Inference & serving216Teacher policy distillation168Medical image segmentation138Physics informed neural130Supervised & diffusion models87Voice AI55Forecasting time49Machine learned interatomic36Remote sensing35Federated learning30Electrocardiogram ecg29Deepfake detection27All 25 fields

Open problems across fields

  • Lack of benchmarks for agent harness reliability1 paper raises it · 1 addresses it

    Existing benchmarks focus on model capabilities rather than the reliability of the systems that support agent operation.

    • Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
  • Unclear net value of agent memory1 paper raises it · 1 addresses it

    Dedicated memory systems often underperform naive retrieval, making their benefits uncertain.

    • Memory Tax: Dissecting the Net Value of Agent Memoryraises · addresses
  • Token collapse in graph soft prompting1 paper raises it · 0 address it

    Graph-specific tokens become indistinguishable, failing to convey intended relational information.

    • On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
  • Poor trajectory supervision for tool-use agents1 paper raises it · 1 addresses it

    Successful trajectories may lack compositional coverage or decision grounding, limiting agent learning.

    • Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agentsraises · addresses
  • Uneven evaluation of coupled agent-world model systems1 paper raises it · 1 addresses it

    Separate evaluation of agents and world models fails to predict their joint performance or sustained learning.

    • Dual Exam: Controlled Evaluation of Multimodal Agents and World Modelsraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

  • Anomaly detectors23+53.3%
  • Channel state information15+36.4%
  • Character recognition OCR12+20.0%
  • AI tutors14+16.7%
  • Multimodal emotion8+14.3%
  • Physics informed neural130−11.0%
  • Machine learned interatomic36−18.2%
  • Supervised & diffusion models87−26.3%

Papers

  • arXiv cs.LGOct 12

    Online LLM Personalization from Pairwise Preferences Across Users

    Romain Puech, Georgy Salakhutdinov, Dimitris Bertsimas

    Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions. We study inference-time personalization through online selection from a fixed set of prompts, each representing a persona. Users arrive sequentially, each asks a short sequence of questions, and the system displays two responses per question and observes one pairwise choice. We formulate this interaction as a variant of the contextual dueling bandit problem in which the learner starts without preference data, adapts within each session, and exploits information shared across users. The objective is to minimize cumulative strong regret, summing the utility gaps of both displayed responses relative to the user's best response among the available options. We make two contributions. First, we introduce the problem and release a reproducible preference benchmark and dataset built around a tutoring case study, containing educational questions, LLM-generated answers in six teaching styles, and pairwise judgments from LLM-simulated students with hidden preference profiles. We fit Bradley-Terry models to these judgments to obtain reference…

    PDF
  • arXiv cs.LGOct 12

    MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs

    Zile Wang, Zhide Xie, Tao Ji

    Multi-Head Latent Attention (MLA) compresses the KV cache into a latent representation, reducing inference memory and bandwidth. Existing MHA2MLA/TransMLA methods do not support QKNorm and require costly recovery on modern LLMs, especially MoE. We present MLAfication, a QKNorm-compatible, parameter-efficient extension of MHA2MLA. It combines calibrated KNorm, parameter-efficient distillation, contribution-aware Partial-RoPE, and activation-aware joint KV initialization. Across MHA and GQA models, including QKNorm- and MoE-equipped variants, MLAfication preserves performance under substantial KV-cache compression, surpasses the current SOTA on commonsense and long-context benchmarks, and extends MLA conversion to modern architectures. On Qwen3-30B-A3B, MLAfication delivers up to $5.35\times$ the serving throughput of BF16 GQA and, combined with 4-bit KV quantization, reduces the KV-cache footprint by $94.73\%$. Our code is available at https://github.com/JT-Ushio/MLAfication.

    PDF
  • arXiv cs.CVOct 12▲ 73

    Multics: Generative Multi-Player World Model with Hierarchical Communication

    Kaiyi Huang, Wangbo Yu, Yukun Huang, Jiwen Yu, Kunhao Liu +4

    Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging. Existing approaches that rely on fully-connected communication (e.g., Solaris) incur quadratic attention costs as the number of players grows, while centralized approaches (e.g., $γ$-World) suffer from interference between unrelated events in a shared global representation. To address these challenges, we present Multics, a multi-player video generation framework with hierarchical communication that structures information exchange across player, group, and global levels. This hierarchy introduces group tokens into self-attention as intermediate group-level representations that aggregate locally relevant player information. These tokens connect to global tokens for cross-group communication, while the hierarchical topology limits direct mixing between unrelated local events. Group-token parameters are shared across group slots, allowing the same communication module to accommodate varying numbers of players without introducing new group-specific parameters. We further propose…

    Code
  • arXiv cs.SEOct 12

    Deleting Code Without Losing Knowledge: Regenerative Software for Python Libraries

    Thomas Bartz-Beielstein

    In the age of "Software 3.0", when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole source of truth becomes questionable. Fowler advocated for a set of seven primitives, which lay the framework for regenerative software, so that programs can be deleted and rebuilt without losing their knowledge. The knowledge lives in machine-readable records in a tracked directory, from which a *regeneration bundle* is built for each unit. The regeneration bundle is a single file with the module's architecture, intent, decisions, public contract, evaluations, and consumers, but no implementation, plus the one dependency module it may import. The open-source package spotregen implements these primitives and provides a graphical user interface. This report presents a first application of Fowler's primitives to the safety-critical forecasting library spotforecast2-safe. During the first experiments, the Claude Code session that orchestrated the study consumed more than 43 million tokens, almost all of them its own history re-sent with every request. This motivated the switch to an architecture that is built on local models.…

    PDF
  • arXiv cs.CLOct 12

    Welcome to the Age of Agent Ads: Using On-Policy Attacks to Steer Agentic Decisions

    Tim R. Davidson, Marija Šakota, Joshua Joseph, Robert West

    People increasingly delegate option-ranking tasks (e.g., shopping, job search, travel) to AI agents, which creates incentives to steer agentic decisions via "agent ads." To defend against such steering attacks, people count on models' alignment training and platforms' terms of service, and consequently the most effective existing attacks are designed to trigger off-policy behaviors. Exposing a new attack surface, we introduce on-policy attacks, which steer agentic decisions without pushing individually aligned behaviors off policy. Our example attack consists of two steps: To remain compliant with platforms' terms of service, we first inject a truthful negation about a fictitious concept ("Does not contain blizyester") into a product description. This triggers an agent to search the web ("What is blizyester?"), which surfaces planted websites full of fabricated information associating the fictitious concept with harmful implications ("Blizyester linked to dementia"). Trained to keep users safe from harm, the agent penalizes every option missing the truthful negation. Evaluating our attack across four real-world listing datasets, we find some frontier models exposed, enabling an…

    PDF
  • arXiv cs.AIOct 12

    Size Generalization for Diffusion Routing Solvers

    Barak Itzchak Davidovitch, Eli Meirom, Ethan Fetaya, Gal Chechik

    Routing problems, like the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP), are NP-hard and slow to solve for large instances. Diffusion-based solvers can be trained in a supervised way using sets of optimal solutions, and then quickly solve new test instances. However, for large instances, optimal solutions are hard to find, and diffusion models fail to generalize to instance sizes outside their training distribution. Here we describe ResizeCO, a label free size-generalization approach that addresses both the change in statistical properties of larger instances, and the computational challenge of solving them quickly. It uses reinforcement learning on large-scale instances to adapt a diffusion model trained on small instances. Specifically, we adapt GRPO to this problem, using route length as the training signal. ResizeCO also formulates k-opt as a tree search, solved by a beam search on the GPU. In size-generalization experiments on TSP and CVRP instances with up to 10000 nodes, ResizeCO achieves a Pareto front over route quality and time that dominates learned solvers, and also outperforms other solvers at short run times, setting a new…

    PDF
  • arXiv cs.LGOct 12▲ 12

    FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation

    Zekun Shi, Alastair James Arthur Price

    Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stored, while hybrid architectures that add full attention for better recall incur quadratic sequence cost. Alternatively, sparse attention with continued pretraining (CPT) can extend the effective context length. Generalization beyond the trained length remains challenging, however, and CPT can be costly. We introduce FreeSolo, a native sparse attention mechanism with a short-range sliding window branch and a long-range branch that selects keypoint cells for direct token attention. Its linear-time variant, FS-L, learns to prune the prefix before query-dependent selection through short CPT. FS-B searches balanced trees with $O(N\log^2 N)$ algorithmic cost including radix-sort construction. FreeSolo demonstrates better zero-shot length extrapolation than the baselines without long-context fine-tuning.

    Code
  • arXiv cs.LGOct 12

    CartoVec: General-Purpose Location Embeddings from Open Map Data

    Furkan Gursoy

    Geographic coordinates are common inputs in applied machine learning, but latitude and longitude describe position rather than the surrounding environment. Image-grounded location encoders learn this context from satellite or ground-level imagery; structured open map data offers another source of supervision whose utility for continuous coordinate encoders remains less explored. We introduce CartoVec, a coordinate encoder trained to predict Overture-derived land cover, land use, transportation, place and connectivity targets at multiple spatial scales, without image inputs or downstream-task labels. We evaluate frozen embeddings on Census outcomes, Airbnb prices and Philadelphia crime in the US Northeast using spatial block cross-validation. CartoVec has the highest mean performance on most Census outcomes and the highest average across the full suite, with several comparisons close across folds. The findings support open map data as a practical source of reusable location representations with a coordinate-to-vector interface that requires no map lookup at inference. The open-weight model is available at https://huggingface.co/gursoyfurkan/CartoVec.

    PDF
  • arXiv cs.CLOct 12

    Soft Teacher Forcing

    Mohammad Fahes, Cordelia Schmid, Anurag Arnab

    Soft tokens have so far been used to replace discrete chain-of-thought in latent reasoning methods. These approaches typically require multi-stage training and, in some cases, auxiliary modules, yet they still underperform supervised fine-tuning (SFT) on <input, chain-of-thought, output> triples. In this paper, we ask whether soft tokens can be used to improve SFT itself, instead of as an avenue for latent reasoning. We introduce Soft Teacher Forcing (Soft-TF), a simple training algorithm that combines teacher-forced embeddings with soft tokens through random convex combinations. The soft tokens are computed in a single parallel forward pass over the ground-truth sequence. Soft-TF adds no parameters, no external model and no curriculum, and leaves inference unchanged. Experiments show that Soft-TF improves over SFT on GSM8K, MATH, MathQA and AQuA, by +2.1 to +4.1 points on GSM8K across seven Gemma, Llama and Mistral models.

    PDF
  • arXiv cs.CLOct 12▲ 13

    DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck

    Shubham Agarwal, Akshat Gupta, Mike Heddes, Dilara Soylu, Rui Meng +19

    Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fundamental bottleneck: the cost of evaluating progress. In real settings, a single true evaluation, such as a full benchmark or serving trace, can take hours, so a search can afford only a handful of true evaluations. We present DuoDiscover, a search system that jointly discovers what to optimize and how to evaluate progress efficiently, through three mechanisms. First, each worker in a fleet of coding agents co-discovers an optimization target and a fast, tailored proxy evaluator, which we call a yardstick. The agent then hill-climbs the yardstick rather than the true evaluation. Second, since search can exploit gaps between a yardstick and the true objective, fidelity tests continually recheck each yardstick's ranking and invalidate any that drift. Third, the fleet is bottom-up, with no central decomposition of the problem. A lightweight orchestrator spawns and terminates agents, briefs running ones, and seeds new agents with others' confirmed work. DuoDiscover enables autonomous optimization from…

    PDF
  • arXiv cs.AIOct 12

    ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning

    Aotian Chen, Frazier N. Baker, Reza Averly, Shan Zhang, Tianao Chen +3

    Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effect occurs. We introduce ChemExplain, a benchmark of 1,180 multiple-choice chemistry questions drawn from 383 peer-reviewed papers. Each question pairs a molecular or reaction image with an observed chemical effect and four candidate explanations, each associated with a different structural feature visible in the image. Answering requires the model to perceive the depicted structure, apply chemical knowledge, and identify which feature most directly explains the effect, a capability we term explanatory attribution. The correct feature-mechanism relation is derived from supporting evidence in the source paper rather than invented by the question-generation LLM. We construct the benchmark automatically with a multi-agent framework that applies progressive quality control at three stages and validate it with eight chemistry domain experts. The strongest evaluated model reaches 78.6% accuracy, leaving considerable room for improvement. On a 600-question expert-reviewed subset, reasoning-trace analysis classifies…

    PDF
  • arXiv cs.LGOct 12

    ModRes: A modification of the ResPlan dataset ready for floor plan analysis and graph machine learning

    Emma Shelley, Wassim Jabi, Thomas Woolley, Katerina Kaouri

    Floor plan datasets underpin computational analysis of building layouts, spatial connectivity and graph machine learning. However, publicly available datasets often require substantial preprocessing before they can be used reliably. We present ModRes, a cleaned and enriched version of the ResPlan dataset, containing 8,431 valid and unique residential floor plans. Invalid and duplicate floor plans are removed through a dedicated cleaning workflow, producing a ready-to-use dataset. For each floor plan, ModRes provides two-dimensional geometry, images, three-dimensional building representations and three complementary dual graphs in CSV and JSON formats with graph-, node- and edge-level features. Continuous and categorical graph attributes support machine learning workflows. We characterise the dataset using graph-based statistics and demonstrate its utility through a range of case studies. ModRes provides structured geometric, topological and semantic representations needed to automate spatial analysis and support machine learning-based workflows for building design and performance evaluation.

    PDF
  • arXiv cs.LGOct 12

    FunDM: Cheap & Label-Free Decision Models from Frozen Language Models

    Ujjawal K. Panchal

    Decision models such as Jev score candidate answers or actions. A small decision head trained label-free can recover about 99% of a frozen language model's multiple-choice accuracy while using only two-thirds of its transformer layers. It learns the full model's answer probabilities with KL divergence, without correct-answer labels for training. One backbone pass reads the question and all options together; the head returns probabilities for every option. We call this model FunDM (Fun Decision Model). Using 24 of Qwen3-8B's 36 layers and skipping the LM head, its +1T variant reaches 75.0% mean accuracy over eight benchmarks, versus 75.7% for the full model. On MMLU-Pro, both heads achieve 1.56 to 1.57 times batched vLLM throughput with about one-third lower peak GPU allocator memory. Both heads score higher than released Contrastive Language Models (CLM), fine-tuned CLM, and CLM-shaped heads trained from scratch on the eight multiple-choice benchmarks and coding-agent selection. Separately trained agent heads learn judge probabilities without pass/fail labels and select passing runs for 74.4 to 74.6 of 100 held-out tasks on average, versus 74 for the full-model judge and 52.0 for…

    PDF
  • arXiv cs.ROOct 12

    Generative Flow on Symbolic Abstractions for Embodiment Capability Discovery

    Youwei Yu, Lantao Liu

    Achieving complex, long-horizon robot behavior remains challenging because successful execution depends on skills grounded in a robot's physical affordances. Existing training-task distributions are often handcrafted or sampled from large language models (LLMs), relying on semantic plausibility rather than embodiment-specific feasibility. This mismatch can produce curricula that are too difficult, redundant, or blind to non-obvious but learnable behaviors. We propose Generative Flow on Symbolic Abstractions (FOSA), a framework for discovering embodiment-specific capabilities by learning a grounded task generator. FOSA parameterizes an abstract policy as a Generative Flow Network that constructs symbolic task skeletons. Each skeleton is compiled into a simulation environment, where low-level policy-learning performance provides the reward signal for the abstract policy. Across heterogeneous robot platforms, FOSA discovers diverse and executable tasks near the robot's empirical capability frontier. After distilling the discovered task policies into a single language-conditioned policy, FOSA improves performance on unseen complex and long-horizon tasks. The code and demonstration…

    PDF
  • arXiv cond-mat.mtrl-sciOct 12

    Comprehensive Workflow for Uncertainty-Aware Ionic Liquid Solvent Discovery

    Alexander Lobo, Urvi Awasthi, Leonid Zhukov

    Designing synthesizable materials with targeted properties remains one of the central objectives in materials sciences. Ionic liquids (ILs) are well suited to this goal due to their "tunability", where physical and chemical properties can be precisely customized by modifying their molecular structure, specifically by varying the combination of cations and anions. At the same time, current data-driven property models for ionic liquids often degrade in scarce, noisy, and uneven data regimes, where measurements cover only a small fraction of chemical space and a limited range of thermodynamic conditions. This makes out-of-distribution screening brittle: even when point predictions look plausible, it is difficult to compare candidates consistently, quantify downstream implications, or trust rankings enough to guide molecular discovery. We present a property-prediction and optimal candidate selection workflow that treats data processing, deep learning modeling, and physics-based calculations as a coupled system, linking property prediction with uncertainty estimation and physics-based filtering. By tightening the link between predicted properties and the criteria used for…

    PDF
  • arXiv cs.AIOct 12

    Learning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors

    Farhad Pashakhanloo, Venkatesh N. Murthy

    The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecules, whereas natural odors contain tens to hundreds of components, adding extra layer of complexity to percept formation. Here, we explore the relationship between molecular composition and perceived similarity in natural odor objects. We study this using a database of more than 1,200 volatile-compound-in-food mixtures containing more than 8,000 molecular components, and use large language models (LLMs) as a scalable surrogate for deriving mixture-level perceptual descriptions. We find that language-derived representations provide useful supervision for predicting held-out mixture similarities from molecular composition. The prediction was consistently strongest when perceptual targets were derived from chemosensory prompts than from other sensory prompts. Further, during the mixture-level training, we learned low-rank molecular embeddings that enabled better prediction of held-out mixture similarities than component-overlap metrics, even for mixture pairs with no shared molecules. Although no single-molecule labels were used during…

    PDF
  • arXiv cs.ROOct 12

    Force-Modulated Dexterity: Unified Compliance for Contact-Rich Manipulation

    Ying Yuan, David Held, Jitendra Malik, Haozhi Qi

    Teleoperation is widely used to collect high-quality demonstrations for robot learning. Dexterous manipulation, however, requires coordinated control of motion and contact forces. Operators can specify motion, but struggle to reproduce the subtle force adjustments of human manipulation without feeling the robot's contacts. We introduce Force-Modulated Dexterity (FOMO-Dex), a unified compliance formulation for contact-rich manipulation. FOMO-Dex expresses nominal actions in coordinates defined by task geometry and contact structure. It applies force-driven motion corrections along selected directions while leaving the remaining command components unchanged. Across card picking, paper cutting, screwdriving, and nut-and-bolt assembly, FOMO-Dex reduces excessive contact forces compared with stiff control. A user study shows that operators collect more successful demonstration data per hour after brief practice. For policy learning, imitating the corrected actions improves card-picking success over imitating raw operator commands. Policies trained on FOMO-Dex demonstrations also achieve more rotation in nut-and-bolt manipulation and screwdriving than those trained on demonstrations…

    PDF
  • arXiv stat.MLOct 12

    A Generalized McDiarmid Inequality: Sample Reuse and Non-Uniform Unbounded Differences

    Jeremiah Birrell

    We develop a novel generalization of McDiarmid's concentration inequality and use it to obtain a uniform law of large numbers result and error bounds on stochastic optimization problems which simultaneously incorporate two key features: 1) They capture the benefit of training sample reuse in algorithms that also employ easily-sampled auxiliary random variables. 2) They allow for one-component mean-difference bounding functions which are both unbounded in the component of interest and have non-uniform dependence on another component. We demonstrate the utility of our method by deriving concentration inequalities for score-based generative modeling. This application naturally leverages both key features of our new tools: 1) It utilizes auxiliary Gaussian random variables in conjunction with the training samples; accounting for training sample reuse results in tighter error bounds by effectively integrating out the dependence on the auxiliary random variables. 2) The ability to handle non-uniform mean-difference bounding functions allows us to treat unbounded score models and data distributions with unbounded support.

    PDF
  • arXiv cs.AIOct 12

    The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express

    Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh, Jack Ji, Jithin Pradeep

    When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1--5 rating, 0--100 score, or comparison) is rarely justified or ablated. Holding the candidate pool, judge prompt, decoding and selection budget fixed, we score 15,406 UltraFeedback candidates under five formats with three judges, curate, fine-tune 66 models, and evaluate them with four judges. A 0--100 scale is worth only 7--12 equally used levels, two to three times a 1--5 scale rather than twenty, and a binary verdict leaves the top score tied in 77--78\% of prompts, so most selections are made at random. These properties are set by the format almost independently of the judge. Kendall's $τ_b$ hides them: it ranks binary best while $τ_a$ and top-1 agreement rank it last, because it discounts the ties a selector must break at random. Both comparative formats inherit a slot bias whose sign differs across judges. Downstream, curated data beat random selection under every evaluation judge, robust to length and markdown adjustment, but no ordering among formats is detectable. We propose four quantities that judge-based curation pipelines should report.

    PDF
  • arXiv cs.ETOct 12

    Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells

    Ning Zhang, Arto Nurmikko

    Decoding visual stimuli from the spiking activity of retinal ganglion cells (RGCs) informs both our understanding of the retinal code and the design of visual prostheses. Natural vision is dynamic, yet state-of-the-art decoders mostly reconstruct single frames with artificial neural networks that process dense, continuous-valued signals rather than the retina's sparse, asynchronous spikes. We asked whether dynamic scenes can be reconstructed and tracked entirely within the spike domain, and at what computational cost. We built an end-to-end spiking neural network (SNN) whose neurons integrate the recorded RGC spikes over time. Populations of up to 1836 RGCs were recorded ex vivo from mouse retina on high-density microelectrode arrays while flashed images, moving bars, drifting gratings and randomly moving handwritten digits were presented. For moving digits, one shared spiking encoder fed two readouts, one reconstructing the image and one decoding the digit's position. Compute energy was estimated from counted synaptic operations. The SNN decoded what and where at once. It reconstructed the stimuli with a structural similarity (SSIM) of up to 0.93, refining the reconstruction as…

    PDF
Load more
PDF
PDF