machine learning

RSS

31
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing arxiv.org
WeVisDoc introduces a two‑stage data‑centric pipeline for end‑to‑end document parsing. Stage I expands coverage using heterogeneous data and structure‑preserving degradations. Stage II probes the Stage I model with a held‑out set, clusters residual errors, and directs targeted data creation and token‑budget reallocation. The 4‑billion‑parameter model reaches 95.38 Overall on OmniDocBench v1.6 and…
Hugging Face Daily Papersarxiv.orgHao Yu, Kang Liu, Linnan Zhao5d1 minpaper
32
AI for Games in the Foundation Model Era arxiv.org
The paper surveys how foundation models are used across six roles in the game development lifecycle—from playing agents to design assistance and runtime adaptation. It highlights limited transferability due to game-specific interfaces and notes that evaluation is mature for bounded play but weak for adaptive and testing scenarios.
Hugging Face Daily Papersarxiv.orgMeng Luo, Yanlin Li, Hao Li7d1 minpaper
33
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models arxiv.org
Latent Interface Training (LIT) first learns a goal‑conditioned action prior without visual input, then adds a pose‑supervised latent interface as the only visual conditioning path. Applied to several vision‑language‑action models, LIT cuts vision‑action shortcuts and lifts LIBERO‑Plus success by 3.9–10.7 points and real‑world task success by 13.3–16.7 points under distribution shifts.
Hugging Face Daily Papersarxiv.orgJianman Lin, Shailesh Shailesh, Zhongyi Luo11d1 minpaper
34
Heretic removes restrictions from language models heretic-project.org
Heretic is an open‑source Python package that claims to strip safety or policy restrictions from LLMs so they obey any prompt. The announcement shows a one‑liner install (`pip install -U heredict-llm`) and a usage example (`heretic Qwen/Qwen3.5-4B`). Links to GitHub, Hugging Face, Discord and Matrix are provided, but no technical details, design rationale, benchmarks, or code snippets beyond the…
Hacker News front pageheretic-project.org1d1 minreleaseHN19380
35
Verifiable Social Reasoning for LLM Assistants arxiv.org
The paper introduces Fuse, a multi‑agent simulation that gives LLM assistants a verifiable ground‑truth task for social reasoning by hiding a target agent’s motive and letting a user‑mediated conversation infer it. Experiments on 12 LLMs show user mediation makes reasoning harder, models are biased by user framing, need more detail than humans, and longer chats don’t always help.
Hugging Face Daily Papersarxiv.orgAmir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush7d1 minpaper
36
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation arxiv.org
RiskChainBench is a new benchmark that pairs synthetic obfuscated message restoration inputs with human‑labeled local web environments, requiring models to both decode malicious instructions and investigate the linked site. Across ten models, restoration accuracy varies widely and web‑agent failures dominate the error budget.
Hugging Face Daily Papersarxiv.orgZhuoXin Liu, Zhiming Ma, Ying Zhang7d1 minpaper
37
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization arxiv.org
This paper introduces SpectralShift, a spectral reparameterization method for extending the context window of Gated DeltaNet (GDN) linear attention models. It reconfigures the decay spectrum by enhancing slow propagation and preserving fast-decaying modes, consistently improving long-context capabilities during continual pretraining.
Hugging Face Daily Papersarxiv.orgZian Liu, Yiwen Hu, Zican Dong9d1 minpaper
38
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills arxiv.org
GraphSkillEvo encodes LLM agent skills as directed graphs and applies population‑based evolution (mutation, crossover) to optimise them. Across five benchmarks it beats the SkillOpt baseline, gaining up to 4% accuracy on GPT‑5.4‑nano.
Hugging Face Daily Papersarxiv.orgRui Sun, Zhi Zheng, Zhenkun Wang4d1 minpaper
39
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents arxiv.org
EvoSkill‑GUI lets GUI agents revise their procedural skills on‑the‑fly without extra training by using a reflect‑revise‑reuse loop that edits skill packages during execution. The approach yields up to +16.2% improvement on MobileWorld and similar gains on AndroidWorld and OSWorld, and the evolved skills transfer to related tasks.
Hugging Face Daily Papersarxiv.orgBofan Chen, Boxuan Zhang, Fei Tang7d1 minpaper
40
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement arxiv.org
The paper introduces Generalized Agent Iteration (GAI), a formal framework that unifies classical iterative policy improvement (GPI) and recursive self‑improvement (RSI). GAI treats an agent as a set of modifiable components and models learning as a loop of evaluation and improvement. Two binary “dials”—whether the improvement mechanism is internal to the agent and whether the evaluation standard…
Hugging Face Daily Papersarxiv.orgHongyao Tang, Yi Ma, Pengyi Li11d1 minpaper
41
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents arxiv.org
EvolveTrade is a framework for self-evolving LLM trading agents that refines their tool-use policies (system prompts) based on past performance. It demonstrates improved Sharpe Ratio and Cumulative Return compared to agents with static policies across various market regimes.
Hugging Face Daily Papersarxiv.orgSehee Kim, Yumin Choi, Minki Kang7d1 minpaper
42
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control arxiv.org
Zing‑0.5 is a 5 B autoregressive world model that lets users control generated environments in real time using both keyboard actions and text prompts. The paper introduces unified action‑text conditioning, segment‑level teacher distillation, and a low‑cost streaming inference pipeline that runs at 24 FPS (832×480) for about $0.009 per minute, achieving 81 % overall and 88.5 % consistency on a nav…
Hugging Face Daily Papersarxiv.orgMingyang Chen, Shengdong Chen, Xiaoxiao Fu7d1 minpaper
43
Calibrating Teacher--Student Discrepancy for On-Policy Distillation arxiv.org
This paper introduces Calibrated On-Policy Distillation (Cal-OPD), a method to improve knowledge distillation by filtering out the teacher model's inherent deviations from the learning signal. Cal-OPD estimates and removes the teacher's self-deviation, leading to better student performance on mathematical reasoning tasks.
Hugging Face Daily Papersarxiv.orgQiangqiang He, Jin Li, MingCai Chen4d1 minpaper
44
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus arxiv.org
This paper investigates the "lossless" claim of Orthrus, a hybrid architecture for accelerating LLM inference. It finds that under BF16 precision, Orthrus diverges from the exact autoregressive output trajectory in over 50% of cases, though FP32 maintains exact matching. Despite BF16 divergence, downstream task performance was not systematically degraded.
Hugging Face Daily Papersarxiv.orgIlya Koziev, Leonid Sinev, Ivan Oseledets8d1 minpaper
45
Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts arxiv.org
Srijika is a system for restyling OpenType fonts across nine Indic scripts by reusing existing template font layout data (GSUB, GPOS). This approach ensures complex script features like conjuncts remain consistent, addressing a major challenge in Indic font generation.
Hugging Face Daily Papersarxiv.orgAnil Pai18d1 minpaper
46
Jev is the fastest-adopted model in AI Gateway history vercel.com
Vercel reports that the Jev decision model was adopted by 13% of paid teams within its first day, outpacing prior model launches. Jev claims to be up to 194× faster and 445× cheaper than general‑purpose LLMs while returning structured, probabilistic decisions.
Vercelvercel.comAmelia Charles4d1 minHN21
47
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation arxiv.org
The authors show that training LLM reviewers on synthetic reviews leads to a compression of rating distributions and loss of semantic diversity, a phenomenon they call scientific-judgment collapse. They mitigate it with TrustReviewer, which uses curated training data and activation steering to preserve judgment diversity.
Hugging Face Daily Papersarxiv.orgSy-Tuyen Ho, Minghui Liu, Furong Huang5d1 minpaper
48
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization arxiv.org
PLC‑DPO extends Direct Preference Optimization by using the policy‑reference margin to route each training pair into clean, flipped, or tie categories, actively correcting noisy or ambiguous labels. Across extensive benchmarks it improves mean win‑rate from 55.5 % to 60.5 % and stays stable under injected noise and tie stress tests.
Hugging Face Daily Papersarxiv.orgBoryeong Cho, Sumyeong Ahn, Se-Young Yun22d1 minpaper
49
★ Detecting spam and auto-replies with Jev and the Laravel AI SDK freek.dev
Jev is a "System One" AI model focused on classification, providing calibrated probabilities for predefined answers rather than generating text. This article demonstrates its use with the Laravel AI SDK to replace complex rule-based systems for detecting spam and auto-replies in a helpdesk application.
Freek Van der Hertenfreek.dev4d6 min
50
Bypassing inference bottlenecks: Accelerating complex AI search with Retrieve-for-Train research.google
Retrieve-for-Train addresses LLM inference bottlenecks in complex AI search by using offline reinforcement learning to train a lightweight diffusion model. This enables efficient, single-pass generation of diverse, property-aligned sub-queries, bypassing slow autoregressive reasoning.
Google Researchresearch.google6d8 minHN2
51
Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation arxiv.org
This paper introduces a training-adaptive Convolutional Sparse Coding (CSC) framework where the sparsity coefficient is learned end-to-end via FISTA unfolding. It uses an information bottleneck perspective to balance representation compression and content preservation, showing improved robustness to input perturbations on CIFAR and ImageNet.
Hugging Face Daily Papersarxiv.orgMeng'en Qin, Yinchen Liu, Mingxuan Cui5d1 minpaper
52
Disentangling Representation Evolution in Transformers through Directional Decomposition arxiv.org
The paper decomposes transformer representation updates into parallel and perpendicular components, showing that parallel updates beyond the residual path are significant. Suppressing parallel updates during pretraining improves validation loss and downstream metrics.
Hugging Face Daily Papersarxiv.orgShwai He, Haichao Zhang, Shen Yan8d1 minpaper
53
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads arxiv.org
This paper introduces HEAL, a method to identify and mitigate hallucinations in Multimodal Large Language Models (MLLMs). It finds that hallucinations stem from information distribution drift in "synergy heads" within the attention mechanism and proposes dynamic calibration to steer output towards factual evidence.
Hugging Face Daily Papersarxiv.orgMeng'en Qin, Junye Chen, Jucheng Liu17d1 minpaper
54
Learning Foresight without Explicit Trajectories for 3D Diffusion Policies arxiv.org
This paper introduces Movement Trend Guidance (MTG), a method to provide foresight to 3D diffusion policies for robotic manipulation without explicit trajectory planning. MTG learns a compact latent representation of interaction evolution, significantly improving performance on various benchmarks with minimal parameter overhead.
Hugging Face Daily Papersarxiv.orgZhongbo Zhang, Zaibin Zhang, Yifan Wang5d1 minpaper
55
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents arxiv.org
CERA-MoA proposes a reinforcement‑learning loop where a router and a set of LLM agents are trained together. A “familiarity” estimator reads mid‑layer hidden states to predict each agent’s competence on a query, letting the router activate only a minimal subset of agents that meet a cumulative confidence threshold. The system also feeds targeted training examples to agents based on their evolving…
Hugging Face Daily Papersarxiv.orgJiaxuan Jiang, Liyuan He, Zhixuan Fang6d1 minpaper
56
PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control arxiv.org
PhysStream introduces a two‑stage autoregressive video generator that uses online‑derived positional and tracking maps (structured scene memory) and sparse velocity‑increment signals to enable fine‑grained, physics‑grounded control of multi‑object tabletop scenes. It cuts motion distribution error by 33 % and trajectory error by 12 % versus strong baselines, and wins 85 % of human preference test…
Hugging Face Daily Papersarxiv.orgChuhao Chen, Peter Wonka, Chaoyang Wang7d1 minpaper
57
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation arxiv.org
The paper shows that when specialist LLMs are trained only on QA pairs (no explicit reasoning supervision), their optimization implicitly selects a latent distribution of reasoning trajectories. By treating the distilled student as an agnostic probe—since it inherits only the sampled trajectories—the authors empirically demonstrate a strong correlation (across 27 specialist‑student pairs) between…
Hugging Face Daily Papersarxiv.orgYilei Tu, Zihao Li, Shaoxiong Ji10d1 minpaper
58
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States arxiv.org
Mind2Dialogue introduces a psychology‑guided simulator that generates user mental states and uses privileged distillation to train LLM assistants on Oracle responses that know those states. The resulting models improve personalization and theory‑of‑mind metrics by up to 41 percentage points versus standard instruction‑tuned baselines.
Hugging Face Daily Papersarxiv.orgZixuan Wang, Yufan Zhou, Jinzhou Tang8d2 minpaper
59
CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design arxiv.org
CADWorld is a new benchmark suite of 200 long‑horizon mechanical CAD tasks in FreeCAD, covering sketching, part modeling, assembly, CAM, FEM, and more. Agents interact via screenshots and GUI actions; success is checked by executable validation of the saved CAD artifacts. Seven existing agents achieve at most 17.5 % success versus an 87 % expert baseline, highlighting the gap between GUI competen…
Hugging Face Daily Papersarxiv.orgZihan Dong, Yuanzhe Liu, Zhiyuan Ma8d1 minpaper
60
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation apple.com
Apple researchers propose Trajectory‑Shaped Discrete Flow Matching (TS‑DFM), a training‑time distillation method that replaces blind stochastic jumps in discrete flow‑matching with an energy‑based compass to select higher‑quality intermediate tokens. On a 170 M‑parameter language model, the 8‑step student outperforms the 1 024‑step teacher by 32 % perplexity while being 128× faster, beating basel…
Apple Machine Learning Researchapple.com6d1 minpaper