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
NewsResearchStacksFor AI agentsAPI
Fields · this week
All fields2047Multimodal340Frontier LLMs264Recursive self improvement217Inference & serving171Agents & indirect prompt injection162Neural operators141Robotics141Clinical reasoning128Forecasting time97Linear bandits71Voice AI60AI safety36Character recognition OCR36Molecular property prediction35Federated learning28All 23 fields

Rising research topics

  • Diffusion priors20−4.8%
  • Character recognition OCR36−5.3%
  • Quantum machine learning25−13.8%
  • Voice AI60−15.5%
  • Spiking neural networks6−25.0%
  • Molecular property prediction35−31.4%
  • Forecasting time97−32.6%
  • Robotics141−32.9%

Open problems across fields

Open problems for this view are being prepared; they appear within a day.

Papers

  • arXiv cs.CLSep 29

    It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them

    Nagham Omar, Mahmoud Jabarin, Kinan Ibraheem, Lotem Peled-Cohen

    Vision-language models (VLMs) are increasingly used in place of human annotators, making it important that substitutability tests reflect the model rather than incidental evaluation conditions. We introduce MIST, the Misleading-Image Stress Test: 200 English sentences, each built around a phrase readable either figuratively or literally and shown with an aligned image depicting its reading, a misleading image depicting the opposite, or no image at all. The guidelines require the label to be decided from the sentence alone, so no image should change any answer. We expected each image to pull a judge's labels toward the sense it depicts, and neither kind did. Across thirteen VLM judges, an aligned image changed 20.5% of labels and a misleading one 19.4%, close for every judge and both above the 11.6% produced by deleting the ignore-the-image instruction with the image left in place. Yet only 37% of the labels that differ between the two images moved toward the sense shown, and agreement with our human annotators is unchanged whether the image is absent, aligned or misleading. The effect is smaller in the seven judges that pass the alt-test than in the six that never do, but present…

    PDF
  • arXiv cs.CLSep 29

    One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification

    Bhanu Prakash Vangala, Vangala Navya

    In the Global South, the lower-income countries of Africa, Asia, and Latin America where most of the world's languages are spoken, a deployed text classifier usually runs on ordinary CPUs, serves many languages with a single model, has few labeled examples in any of them, and relies on people to catch its mistakes. Such a system is only useful if it can promise how often it will be wrong: at most a fixed fraction of the labels it assigns on its own may be incorrect, and everything else must go to a person. Split conformal prediction delivers this promise through a single confidence threshold, normally estimated on validation data pooled across languages. We ask whether the promise reaches every language, and it does not. On MasakhaNEWS (16 African languages) and AfriSenti (12 languages plus two never seen in training), a pooled threshold meets the 90% target on average but covers Somali at 77.5%, Tigrinya at 83.7%, and the two unseen languages at 77.5% and 81.2%. Estimating one threshold per language brings every language to between 89.1% and 91.0% without retraining, and it shows how unequal the cost of the promise is: keeping it means sending 43% of Somali news and over 80% of…

    PDF
  • arXiv cs.LGSep 29

    Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearning

    Tianhao Qian, Ziming Hong, Chongyang Gao, Kezhen Chen, Lixu Wang

    Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most associated with a target, however, need not be the best ones to update, and candidate interventions can change value as optimization proceeds. In a controlled experiment, a storage-localization score reaches an area under the receiver operating characteristic curve (AUROC) of 0.981, yet storage identity agrees with the better intervention on only 17/36 targets, while low-rank adaptation (LoRA) wins 35/36. We introduce Intervention Score, which ranks editable groups by the predicted effect of the actual unlearning update while accounting for collateral damage, and use it to form the static intervention-value baseline (Static-IV). We then introduce selective dynamic intervention re-ranking (DIR-R), which revisits that subset only when a calibrated probe justifies the comparison. On the Natural-TOFU dataset, our method has positive descriptive margins in 19/20 comparisons between methods and objectives, although several are near zero. On the LACUNA localization-precision benchmark, our mean terminal utility…

    PDF
  • arXiv cs.AISep 29

    Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability

    Zhenting Huang, Bo Jiang, Junnan Liu, Zhixing Tan, Qianren Mao

    Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large language model activations. However, a feature is useful for interpretation only if it remains a stable unit of analysis when the same meaning is expressed in different surface forms. We study this reliability question for TopK SAEs via feature sensitivity. Experiments demonstrate that scaling selectively reduces the sensitivity of rare features, while common features remain comparatively stable. A controlled width\(\times k\) factorial experiment identifies the active budget k as the root cause: the degradation arises from the selection boundary rather than dictionary width alone. We attribute this failure to the geometry of TopK selection. The active margin, the distance to the cutoff, predicts feature loss without thresholds. Guided by this margin diagnosis, we introduce pairwise rank stabilization. Our method targets ordering failures at the cutoff and improves rare-feature sensitivity by \(8.83\) percentage points, while keeping reconstruction and alive-feature coverage near the baseline. Overall, our results suggest that wide TopK SAEs should be evaluated…

    PDF
  • arXiv cs.CVSep 29

    HandAnthro: Automated Hand Anthropometry from a Single Image

    Fan Zhou, Shuairan Chen, Mengying Zhang, Yulin Wu, Sadegh Jafari +4

    Hand anthropometry supports protective-glove design, but existing measurement methods often require trained operators, specialized hardware, or manual landmarking. We present HandAnthro, which estimates 44 projected hand dimensions from a smartphone photograph of a palm-up hand on US letter-size paper. The pipeline reconstructs wrist-occluded paper boundaries for rectification, whitens non-hand pixels, and refines 41 anthropometry-specific landmarks from a fine-tuned You Only Look Once (YOLO) pose model using image-specific geometry and contours. Controlled evaluation comprised 720 captures from 45 held-out participants, each contributing 16 images across two smartphones, two backgrounds, two angles, and two nominal illumination settings. HandAnthro produced complete outputs for 704 captures (97.8%); among these, mean absolute error (MAE) was 3.80 mm per dimension against two trained operators' caliper measurements. Regional MAEs were 2.48 mm for non-thumb fingers, 6.04 mm for thumbs, and 6.17 mm for palm and wrist. In a researcher-assisted mobile-app pilot, automated batch processing returned all 44 dimensions for 260 of 268 retained, researcher-screened firefighter images…

    PDF
  • arXiv cs.CLSep 29

    AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction

    Wentao Liu, Xi Chen, Siyu Song, Biao Yuan, Yu Zhang +11

    Large language models (LLMs) are increasingly deployed as social agents, yet credible human-like interaction requires more than fluent responses or persona consistency. Agents must autonomously decide whether, when, and how to communicate while adapting to evolving contexts, goals, and relationships. Existing research, however, lacks a unified approach to enabling, evaluating, and improving such capabilities in continuous, open-ended interaction. We introduce AnthroDial, a unified framework for developing anthropomorphic social agents from three complementary aspects: MindFlow, a lightweight interaction harness that enables autonomous, asynchronous, and adaptive communication through a dynamic Mind Buffer; CAPS-Eval, a theory-grounded framework for evaluating cognitive, affective, and behavioral dimensions of anthropomorphic interaction; and a scalable training paradigm that combines SEEDS for environment expansion with DiAPO for adaptive capability optimization. We further construct evaluation datasets covering everyday communication, game interaction, and long-horizon character interaction. Extensive experiments across diverse models and scenarios demonstrate improved…

    PDF
  • arXiv cs.LGSep 29

    Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs

    Haozhan Tang, Hao Kang, Han Cai, Song Han, Chenyan Xiong

    Reliable FP8 attention remains a barrier to fully native 8-bit large language model training. We derive how forward-backward inconsistencies produce stale delta and empirically show how it distorts training dynamics. Our stale-delta hybrid runs show a modest loss gap at 569M parameters but substantial loss increases and downstream degradation at 1.67B and 5.29B. QK normalization, NoPE (no positional encoding), and lower-learning-rate context extension mitigate or delay degradation without eliminating it. This pattern suggests accumulated optimization error that smaller models and short runs can conceal. We propose Delta-Matching, proving that it restores the softmax gradient's zero-row-sum invariant under the stated numerical assumptions. It enables native block-scaled FP8 in every forward and backward attention-core matmul without architectural changes, smaller global batches, or auxiliary forward outputs. Across tested architectures, scales, and training stages, Delta-Matching matches BF16/FP32 mixed-precision training loss and overall downstream performance. We will release our implementation, trained models, and data recipes.

    PDF
  • arXiv cs.CVSep 29

    FlowMap-OPD: Rollout--Kernel Separation for On-Policy Distillation of Few-Step Flow-Map Generators

    Zhiqi Li, Bo Zhu

    Few-step flow-map generators, including MeanFlow and consistency models, enable efficient sampling through long-range transport, yet their on-policy distillation remains underexplored. We introduce FlowMap-OPD, an on-policy distillation framework that separates student-state acquisition from teacher--student distribution comparison. A formulation based on state marginals establishes this separation, while flow--velocity consistency connects local supervision to the deployed long-range map. Within this framework, we develop flow-map, induced-velocity, and instantaneous-velocity distribution supervision, each paired with a separately specified native flow-map rollout. Cross-capacity ImageNet experiments across three teacher rewards identify instantaneous-velocity distribution supervision with independently tunable student consistency as the most effective choice. In text-to-image experiments, FlowMap-OPD demonstrates strong multi-specialist consolidation capabilities and surpasses multi-reward Flow-Map GRPO in task performance and convergence speed.

    PDF
  • arXiv cs.CVSep 29

    RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution

    Xijun Wang, Xin Li, Zirui Lang, Suhang Yao, Haoran Li +1

    Large generative models can recover realistic detail in real-world video super-resolution (VSR), but processing an entire video with them is computationally expensive. In this work, we present RelayVSR, a streaming VSR framework built on the Sparse Generative Relay mechanism. A large generative model generates reference latents for sparse keyframes, while a lightweight VSR network uses these references and low-resolution video to super-resolve every frame. The lightweight VSR network, implemented as a Dual-Memory Video Transformer, reuses keyframe information across frames and updates recent video context, supporting first-keyframe conditioning and dual-endpoint conditioning with bounded lookahead. However, errors in shared keyframes can propagate and accumulate across output frames, making keyframe quality alone an insufficient optimization target. We address this collaboration gap with Video-Aware Reference Optimization (VARO), which uses reinforcement learning to update the large generative model with two reward levels: a system-level reward evaluates videos produced by the fixed lightweight VSR network, while a reference-level reward evaluates decoded keyframe quality. VARO…

    PDF
  • arXiv cs.SESep 29

    Is manual software optimization a thing of the past?

    Pavlin G. Poličar, Martin Špendl, Tomaž Hočevar

    Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditionally requires substantial expertise in programming, algorithms, and numerical methods. Recent advances in large language models (LLMs) offer the possibility of automating much of this process. We investigate whether LLM-based agents can autonomously achieve substantial performance improvements in scientific software, including mature implementations that have already been extensively optimized by human developers. We tasked an LLM-based agent with optimizing software for three computational problems: t-SNE, single-sample gene set enrichment analysis (ssGSEA), and graphlet counting. Humans defined the scope, correctness criteria, and a verification mechanism, after which the agent worked autonomously, in some cases for several hours. Code maintainers reviewed each resulting implementation and verified its correctness. The optimized implementations were faster in all tested configurations, by up to two orders of magnitude over the fastest existing tools. The improvements included low-level code optimizations, mathematical…

    PDF
  • arXiv cs.CVSep 29

    Evaluation Choices Shape Biomedical ML Claims: A Pediatric Pneumonia Benchmark Case Study

    Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi, Navya Vangala

    Biomedical machine learning papers often compress model performance into one headline number. That number can look like a property of the model even when it depends strongly on how the benchmark was evaluated. We study this problem on the widely used Kermany pediatric chest radiograph dataset using nine image classifiers and a controlled evaluation protocol. Under the same protocol, the eight pretrained backbones differ by only 0.026 AUROC. In contrast, changing whether the backbone is frozen or fine-tuned changes AUROC by 0.044 on average, and changing the decision threshold changes balanced accuracy by 0.090 on average. The official test split is also measurably different from the training pool: a partition classifier distinguishes them at AUC 0.697, rising to 0.898 for normal radiographs. Most strikingly, a classifier using only file properties, with no image anatomy, reaches 0.992 balanced accuracy within the training pool but falls to 0.496 on the official test split. Validation-fitted thresholds and calibration also transfer imperfectly. These results show that a high benchmark score can support different conclusions when the split, training policy, threshold, metric,…

    PDF
  • arXiv cs.LGSep 29

    Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection

    Jaeseung Heo, J Rosser, Dongwoo Kim

    Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influence different behaviors of an LLM involves repeated influence computation. Reusing stored training gradients reduces the computational cost, but storing full gradients is prohibitively expensive at LLM scale. We study how to compress these gradients while preserving influence estimates for future queries that are unknown at storage time. Through a worst-case analysis, we characterize the optimal fixed-dimensional linear representation and propose eigenbasis-corrected one-bit gradient projection (EOGP) to approximate it at scale. Specifically, EOGP uses EK-FAC to reduce gradient dimensionality, then applies PCA within the retained subspace to learn compression directions from the training gradients. We then apply one-bit quantization to the resulting coordinates, allowing more coordinates to be retained within a fixed storage budget. On GPT-2, EOGP predicts retraining outcomes more accurately than the evaluated compression baselines while using one-sixteenth of their per-example storage. On OLMo 2 SFT models from 1B to 32B parameters,…

    PDF
  • arXiv cs.LGSep 29

    Kinematic signatures of impairment: Detecting alcohol intoxication in e-scooter riders using sensor data and machine learning

    Rahul Rajendra Pai, Marco Dozza, Alexander Rasch, Ali Mohammadi, Marco Capuccini

    Alcohol intoxication is a leading contributor to fatal and severe-injured e-scooterist crashes. Current countermeasures, such as temporal restrictions or pre-ride cognitive screening, cannot continuously assess an e-scooterist's physical motor control or impairment in real time. We conducted a controlled experiment in which 25 participants rode an instrumented e-scooter through a test track while sober and at two targeted blood alcohol concentration levels (0.05% and 0.08%). The e-scooter was instrumented with a six-axis inertial measurement unit (IMU), and throttle and brake lever position sensors, all sampled at 100 Hz. Two complementary signal features were computed: normalised permutation entropy, which quantifies temporal complexity, and standard deviation, which quantifies signal amplitude. Repeated measures correlation identified seven kinematic features (all IMU and throttle signals) whose entropy decreased (p < 0.001) while standard deviation increased (p < 0.01) with increasing intoxication, indicating that intoxicated riders shift from continuous, low-amplitude micro-corrections to fewer, high-amplitude reactive corrections. An entropy based multi-class logistic…

    PDF
  • arXiv cs.LGSep 29

    Counterfactual Probing for Parallel Unmasking with Hidden Forest Structure

    Ryotaro Kawata, Satoshi Hayakawa, Taiji Suzuki

    Masked generative models offer parallel token prediction, but accurate parallel sampling must account for dependencies among tokens. When dependencies are unknown, finding safe batches also costs model evaluations. We study whether total evaluations, including discovery, can be sublinear in sequence length $N$; sublinear sequential depth then follows. We consider discrete distributions with hidden forest structure, accessed through a fixed approximate conditional oracle. Under explicit regularity conditions and uniform Hellinger error bounds, for any fixed target accuracy $\varepsilon\in(0,1/8]$ and sufficiently large $N$, our sampler achieves seed-averaged total-variation error at most $\varepsilon$, with total masked-state submissions and sequential depth both bounded by $\widetilde{O}(N^C \varepsilon^{-a})$ for constants $0<C<1$ and $a>0$. These guarantees use polynomial vocabulary size and an edge-response lower bound set by $N$ and $\varepsilon$. The sampler shares evaluations of hypothetical reveals across dependence tests to identify safe parallel batches without requiring full recovery of the hidden forest. A tunable parameter trades probing cost against irreversible…

    PDF
  • arXiv cs.CLSep 29

    Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment

    Haotian Deng, Wenbin Xing, Gang Xu, Tao He, Jinkai Zheng +3

    Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses. Existing safety methods often require large preference datasets, costly multi-rollout training, or additional safeguards at inference time. They may also sacrifice helpfulness by directly refusing requests that could be answered safely. In this paper, we propose Intent-Privilege On-Policy Self-Distillation (OPSD), which leverages evidence-grounded intent as privileged supervision during training to help VLMs recognize implicit risks and provide safe, useful responses instead of blanket refusals. OPSD distills a teacher's intent-conditioned preferences over responses into a student using a single rollout per prompt; the student then responds without intent annotations or an additional safety module. With only 1,447 safety-specific examples - 95% fewer than standard preference datasets - OPSD reduces training time by 5x relative to multi-rollout GRPO-style training and average inference length by 7%. It attains the highest ratio for joint safety-helpfulness success, which measures the proportion of responses…

    PDF
  • arXiv cs.LGSep 29

    Behavioral Convergence Without Representational Convergence: Persistent Training-History Dependence in Neural Networks

    Ertuğrul Mutlu

    Neural networks trained toward the same final objective can reach similar predictive performance while retaining internal representations shaped by earlier training history. We study this effect using controlled sequential-training experiments in which paired convolutional networks start from identical weights, experience reversed task orders, and then receive the same deterministic common-relaxation distribution. Across 20 paired MNIST runs, 16 satisfy a predeclared behavioral-matching criterion, yet their matched representations retain a mean history score of 0.139 (95% bootstrap CI: 0.127-0.153) and approximately 3.1% prediction disagreement. Extending common relaxation to 50,000 optimizer updates does not erase the measured difference: across five paired seeds, the representation-history score remains 0.190 (95% bootstrap CI: 0.161-0.219) at the end of the measured horizon while the mean accuracy gap is only 0.18 percentage points. Fresh linear probes show that, with sufficient labeled data, the two histories retain practically equivalent linearly accessible class information. A same-label rotated-MNIST control reproduces the effect: all five paired seeds reach behavioral…

    PDF
  • arXiv cs.AISep 29

    Mixture of Self-Improving Branches For Agent Harness Optimization

    Haoyu Dong, Yuhang Zhou, Zihao Lin, Yifan Wu, Bo Peng +4

    Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes through execution feedback. Recent work such as Meta-Harness implements this process through iterative code generation and evaluation, but retains a fixed development set and proposal policy. These constraints channel evolution along a single search trajectory, increasing the risk of converging to a local optimum. We make the improvement process itself adaptive by organizing search into branches with evolving development subsets and proposal policies. Each branch retains development cases solved by more of its leading harnesses than by those of other branches, drops cases solved by every leading harness across all branches, and revises its proposal policy using its own search history. To deploy the resulting complementary harnesses, we propose a router to select one development-selected branch head for each new input before execution. Across mathematical reasoning and agentic coding benchmarks, our system achieves relative improvements over Meta-Harness of 34.8% on Olympiad-level mathematical reasoning, 11.6% on Terminal-Bench 2.0,…

    PDF
  • arXiv cs.AISep 29

    Can a Cacheable Decision Model Follow Rules?

    Dushyant Rajput, Nirdesh Chauhan, Siddharth Kosaraju

    Certo is a small non-generative decision model (Qwen3-4B): it scores candidate actions from their text and returns a probability, instead of generating an answer. The accurate design reads the state, the rules, and each candidate together (a joint scorer), so cost grows with the menu. Independent encoding lets each candidate be encoded once and reused across states (about 5x cheaper at 77 candidates), but separates state from candidate. We ask how much rule-sensitivity survives that move, and whether it can be trained back. Four experiments on Certo: (1) the tested conversion to cacheable scoring loses rule-sensitivity (recall@1 1.00 -> 0.24) while the joint scorer holds 1.00, and a shortlist+rerank rescue fails; (2) targeted counterfactual supervision restores strong performance on held-out synthetic rule tasks (paraphrase, counterfactual, composition; reproducible across seeds), though we do not isolate whether predictions depend on the supplied rule; (3) on real rules the added benefit is not established -- after fixing a truncation confound, the joint scorer wins significantly on the short tier (0.861 vs 0.500) and directionally on the hard tier (0.655 vs 0.483, n=29); (4) a…

    PDF
  • arXiv cs.CVSep 29

    ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routing

    Xijun Wang, Xin Li, Suhang Yao, Zirui Lang, Bingchen Li +1

    Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise generative fidelity. We propose ReCaVSR, a Wan2.2-based, one-step framework for streaming VSR that builds on two observations: recycled SR latents retain local temporal context, reducing the need for full historical Key-Value (KV) caches; and individual transformer layers benefit from distinct temporal scopes. ReCaVSR combines three complementary designs: (i) layer-wise cache routing with recycled SR latents: each DiT layer learns its KV-cache temporal scope under a cache budget and exports a static inference schedule, while recycled SR latents propagate local context by conditioning each new block on the model's own preceding predictions. (ii) Multi-Scope Query (MSQ) Discriminator: a compositional discriminator combining global, spatial-window, and temporal-tube feedback for holistic realism, local texture generation, and temporal stability. (iii) LR-conditioned adaptation of FlashDecoder: a VAE decoder that incorporates LR observations for efficient latent decoding. ReCaVSR enables streaming VSR without iterative sampling or full…

    PDF
  • arXiv cs.DCSep 29

    When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents

    Yuqiao Meng, Luoxi Tang, Yingxue Zhang, Yuchen Yang, Zhaohan Xi

    Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or memory states evolve. Existing work mainly studies memory content errors or evaluates fixed test cases, leaving memory-use failures hard to discover systematically. We formulate this issue as a fuzzing problem and categorize such failures into query-related and memory-state failures. We then develop U-Fuzz, which starts from memory checkpoints as test seeds, mutates queries or memory states under explicit mutation obligations, validates each mutant, and uses observed memory behavior to guide iterative testing while keeping failure labels outside the search. We evaluate U-Fuzz across several memory systems against diverse fuzzing baselines, and further test an output-only setting with API-based LLMs where memory retrieval is hidden. Across these settings, U-Fuzz consistently uncovers more confirmed memory-use failures, showing that its search remains effective across different memory architectures and even when only final responses are observable.

    PDF
Load more