Tema

LLMs

2972documentos

221últimos 7 días

Developing a Speech Language Model for Basque

Although the recent development of LLMs has paved the way for multi-modal interaction, minority languages face difficulties keeping pace. This work presents the first open Speech Language Model for Basque, designed for low-latency, end-to-end spoken interaction. Based on the LLaMA-Omni architecture, the system integrates a Latxa model as its backbone, transferring its Basque capabilities to the spoken modality by fine-tuning several modules. To address data scarcity, the English VoiceAssistant-400K corpus was translated into Basque, and the audio was synthesized using a Basque TTS. Evaluation results confirm the system's viability, achieving 3.86/5 in content quality, a 9.94% WER for spoken intelligibility, and a 3.07 UTMOS for audio quality. This work demonstrates that advanced spoken interaction systems can be developed using modular architectures and synthetic data even in low-resource languages.

arXiv AI Papershace 17 días

Nothing Left Behind: Finding Evidence from a Large Randomized Evaluation Corpus

Many AI systems need to find every relevant items in a large collection and then organize what they found. The standard way to do this is to tag each item with labels from a curated vocabulary and search on those labels. Those labels are useful for organizing results, but searching on them misses items that do not fit a label and returns too much when labels are broad. We compare this approach with an embedding-based approach: find candidates by meaning using text embeddings, then have a language model keep only the relevant ones. In a corpus of 7,354 randomized trials, label search found 45% of the evidence a systematic review would include, while the new approach found 92%, at a cost per query that rises with search depth. These results support a two-stage architecture that combines broad candidate retrieval with query-specific evidence filtering.

arXiv AI Papershace 17 días

HiLo-RD: Cross-Budget Self-Distillation for Masked Diffusion Language Models

We propose HiLo-RD (High-to-Low Budget Representation Distillation) to improve masked diffusion language models (MDLMs) under a limited generation budget. Unlike autoregressive models, MDLMs choose both what to generate and where to commit it. This creates two coupled challenges: predicting useful content before reasoning is complete, and deciding when to fix answer tokens that shape later predictions. We identify budget-induced premature commitment: even when a correct solution fits, the model can fix answer fragments near the window boundary before resolving intermediate steps. These fragments become context for later predictions and redirect subsequent reasoning. Existing post-training methods do not directly transfer the stronger trajectories that the same model follows with a larger window. HiLo-RD addresses this gap by (1) pairing large-window teacher states with cropped small-window views and (2) matching their hidden representations at committed positions. This supervision guides both token prediction and commitment order without an external teacher. Across mathematics benchmarks, HiLo-RD improves low-budget accuracy and shortens responses; these gains extend to code generation without code-domain training. On GSM8K, accuracy rises by 9.4 percentage points as mean readable length falls by about 25%. Attention diagnostics and fixed-budget order interventions support the proposed mechanism. Together, these results show that large-window reasoning can improve small-window decoding.

arXiv AI Papershace 17 días

GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents

Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large language model or VLM in the loop, making them slow and memory-hungry. To address these issues, we propose GUI-JEPA, to our knowledge the first decoder-free GUI agent policy built on a Joint-Embedding Predictive Architecture (JEPA), which selects actions in the latent space of a JEPA encoder pretrained on unlabelled GUI screenshots. Its action- and region-conditioned latent predictor turns the screen latent into one latent per candidate action, letting lightweight heads score all candidates against the instruction in a single batched pass, without decoding a token. We further show that the scorer relies on this latent pathway and that the predictor is trained for the decision itself: a randomly initialised predictor does just as well as one pretrained on screen dynamics. On AndroidControl, GUI-JEPA is 2.8-4.0x faster on the same GPU than a Qwen2.5-VL-7B agent we fine-tune with the same inputs, while reaching 86-92% of its in-distribution accuracy with 6% of its parameters. Code is available at https://github.com/bcwang-sjtu/GUI-JEPA

arXiv AI Papershace 17 días

When All Rollouts Fail: Policy-Compatible Joint Decoding for Hard-Problem Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) derives its learning signal from binary rewards via on-policy exploration and becomes a powerful paradigm for improving the reasoning of large language models. Yet it faces a learning cliff on problems beyond model's current ability: when every rollout fails, the samples reveal nothing about a correct solution, and group-relative estimators (e.g., GRPO, RLOO) collapse the update to zero advantage. Expert trajectories offer a remedy, but they are incompatible with the current policy and often lie in the student's low-probability regions, so the surviving updates demand large parameter shifts and decay into surface-level imitation rather than transferable reasoning. We argue that a useful learning signal on hard problems must be both verifiably correct and sufficiently compatible with the current policy. We propose Policy-Compatible Reinforcement Learning (PICO), which performs distribution-constrained joint decoding: expert data guides decoding at the token level while preserving the student's relative token probabilities, and a dynamic top-k mechanism confines the sampling distribution under a finite divergence budget, yielding trajectories that are verified and policy-compatible by construction. These trajectories are optimized jointly with on-policy rollouts under a mixed-behavior objective that mitigates their distribution mismatch via importance sampling. Experiments across reasoning diverse datasets and agentic benchmarks demonstrate that PICO consistently outperforms standard RLVR and prior off-policy baselines.

arXiv AI Papershace 17 días

When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement

Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution around large language models (LLMs). While recent work has begun to evolve these harnesses from execution experience, the supervision used to guide evolution often remains relatively static, making it difficult to track changing behavioral weaknesses across rounds and potentially limiting generalization to unseen tasks. To address this issue, we propose RuHarness, a rubric--harness co-evolution framework for continual agent self-improvement. RuHarness continually discovers and reassesses behavioral criteria from execution trajectories, prioritizes the most relevant unresolved weaknesses, and uses them to guide targeted harness updates while keeping the task objective fixed. Extensive experiments across diverse agent tasks and backbone models show that RuHarness outperforms strong harness-evolution baselines, particularly on unseen held-out tasks. Further analyses show that adaptive rubric prioritization tracks shifting weaknesses and supports more sustained improvement and stable generalization across evolution rounds.

arXiv AI Papershace 17 días

Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind

Theory of Mind (ToM), the ability to infer others' beliefs, goals, and intentions, is a cornerstone of social intelligence. Multimodal ToM requires inferring an agent's mental state from evidence that is available to that agent, rather than from the complete episode observed by the solver. Existing LLM-based and Bayesian model-based approaches reconstruct global event traces, yet they do not explicitly distinguish objective events from agent-admissible evidence during hypothesis evaluation. Consequently, agent-inaccessible events or semantically misaligned actions and utterances may influence the inferred belief, goal, or social intention, leading to perspective leakage and source or route confusion. We formulate this limitation as an evidence-admissibility problem: evidence should contribute to a mental-state hypothesis only when it is accessible to the relevant agent, preserves its information source, and is diagnostic of the queried mental-state variable. To operationalize this principle, we propose PIP-ToM, an evidence-admissibility interface that constructs agent-specific evidence stores, aligns them with structured mental-state claims, and calibrates model-based hypothesis scores while preserving the underlying Bayesian inference process. PIP-ToM with GPT-4o outperforms existing ToM methods across MuMA-ToM, MMToM-QA, and Hi-ToM, achieving average accuracies of 92.56%, 95.00%, and 95.00%, respectively.

arXiv AI Papershace 17 días

Weakness Localization Is Not Enough: State-Aware Recursive Knowledge Improvement for Large Language Models

Knowledge improvement in large language models is shifting from predefined knowledge incorporation pipelines toward evaluation-guided updating. Existing methods use evaluation to localize model-specific knowledge weaknesses and guide targeted post-training. However, identifying what to improve does not necessarily provide sufficient information for deciding how to improve it. The same localized weakness can be compatible with distinct operational knowledge states: the relevant knowledge may be unavailable, available but difficult to access reliably, or accessible but ineffective for downstream use. We call this ambiguity knowledge-state aliasing. When compatible states favor different interventions, greater diagnostic resolution alone is insufficient for intervention selection. Moreover, model updates can change the underlying knowledge state before the observed weakness disappears, such that an intervention appropriate in one round may no longer address the bottleneck in the next. To address these challenges, we propose Recursive Knowledge Improvement (RKI), which formulates knowledge improvement as a sequential, state-aware intervention process. RKI organizes knowledge into graph-structured units that provide a shared basis for diagnostic evaluation and targeted intervention across rounds. At each round, RKI localizes knowledge weaknesses, estimates the model's operational knowledge state from diagnostic evidence and intervention history, selects a corresponding intervention, and re-evaluates the updated model before determining the next intervention. On HotpotEval and SafeInternalEval, RKI outperforms existing knowledge incorporation methods by 18.41 points on average. Further analyses show that knowledge states provide additional guidance for intervention selection beyond weakness localization and can change across model updates even when the observed weakness persists.

arXiv AI Papershace 17 días

Latent Visual Contrastive Reasoning with Multi-Branch Exploration

Multimodal large language models have made substantial progress in visual question answering, but complex visual reasoning often requires locating and comparing multiple pieces of question-relevant visual evidence. Existing methods that move intermediate reasoning into the visual latent space usually follow a single linear reasoning trajectory, which can be limiting when multiple visual hypotheses or competing evidence regions are relevant. We propose Latent Visual Contrastive Reasoning, a branch-aware latent reasoning framework that generates multiple question-conditioned latent visual branches as soft hypotheses over image tokens. To train these branches, our method uses bounding-box evidence annotations to build target evidence representations and introduces a soft contrastive branch-evidence alignment objective. This objective encourages evidence-relevant branches to align with annotated visual regions while contrasting them against negative evidence. We instantiate our method on Qwen2.5-VL backbones and train it with standard supervised fine-tuning. Experiments on perception-intensive visual reasoning benchmarks show that the proposed method achieves overall improvements over the corresponding backbone and single-path latent reasoning baselines at both 3B and 7B scales.

arXiv AI Papershace 17 días

SetGRPO: Calibrating Grader-Induced Policy Optimization

Rubric-based reinforcement learning uses fine-grained grader feedback to train large language models on open-ended tasks, but grader randomness can alter GRPO updates in ways that score discrepancies alone cannot characterize. Because GRPO jointly normalizes rewards within each response group and combines the resulting training coefficients with response-level gradients, a scoring discrepancy can shift the coefficients of the entire group and induce policy-dependent update changes. Selective execution further affects the direction-reversal risk of retained updates. To address this, we propose Set-Valued Group Relative Policy Optimization (SetGRPO). It comprises three modules: (a) Joint Reward Set Calibration constructs a joint uncertainty set for the training coefficients; (b) Geometry-Guided Safe Recovery maps candidate coefficients into the current policy's local update geometry and determines the largest safe recovery ratio for each response group; and (c) Selective Risk-Gated Optimization selects a global threshold through independent risk calibration to control the conditional direction-reversal risk of accepted updates while preserving the original GRPO objective. Under exchangeability, SetGRPO provides finite-sample marginal coverage for the joint coefficient set and simultaneous risk control across candidate thresholds. On ten open-ended benchmarks spanning three domains, SetGRPO achieves the highest macro average among all compared training methods on both Qwen3.5 and Llama3.2 model families.

arXiv AI Papershace 17 días

LLM knowledge for improved Out-of-Distribution Tabular Prediction - A Cross-Validated Regularisation Approach

Prediction models degrade when the deployment population differs from the one used to train them, and training data cannot say which feature-response relationships will transfer. Expert elicitation is slow and unscalable. We ask whether coefficient priors elicited from large language models (LLMs) improve out-of-distribution (OOD) prediction as the shrinkage target of a regularised regression instead of zero, across five tabular datasets split on real covariates, selecting providers and prior structures by source-domain cross-validation alone. The priors help on four of five datasets, by up to 7.9% OOD mean squared error, and ten of twenty-four prior-informed results resolve the mean improvement at conventional confidence; single-deployment intervals are much wider. On classification the gain is in probabilistic accuracy, not ranking, and control tests with corrupted priors attribute the benefit to feature-specific content rather than scale. Two findings temper this. Variation across candidate priors exceeds the average benefit, yet cross-validation margins fall below their own noise, so selection avoids the worst prior rather than finding the best. On three datasets the prior improves in-domain accuracy as much as out-of-domain, making it better regularisation than shift correction. Only where the training data are large enough that the in-domain gain disappears does elicited knowledge demonstrably improve transfer. Code, priors and results: https://github.com/hugohammer/llm-priors-ood.

arXiv AI Papershace 17 días

Personality Latents: Conditioning Frozen Language Models on Individuals from Their Own Writing

Controlling the personality of a language model usually relies on written profiles or named trait categories, so it can only express what an author writes down or what a taxonomy names. We instead propose Personality Latents (PL), which learn a latent for each person from their own writing, with no personality labels and no authored profile, and inject it into a frozen language model as a soft prefix. Following generative latent optimization, each training person receives a free latent that is optimized through the frozen model itself, while an encoder learns to predict these latents so that a new person needs only one forward pass, with optional refinement at test time. We evaluate on held-out people by having the conditioned model answer neutral and interview questions and reading personality from its answers with scorers trained on real human writing. On the MBTI axes PL reaches an AUC of , ahead of persona embedding and prompt-based baselines under identical settings, and the ranking holds when the answers are scored in three different embedding spaces. A latent learned with Qwen2.5-3B-Instruct also transfers personality to Llama-3.1-8B-Instruct through a new adapter alone.

arXiv AI Papershace 17 días

API-TAIL: Detecting Model Substitution in LLM APIs through Temperature-Aligned Likelihood Tails

Commercial language model APIs return only text, allowing a provider to cut costs by quietly routing a fraction of user requests to a cheaper substitute model while billing for the advertised one. Detecting such partial substitution is challenging because honest providers also alter the output distribution through undocumented decoding and serving choices, such as temperature scaling, sampling truncation, repetition and presence penalties, and default system prompts, forcing an audit to test against a composite null of legitimate configurations rather than a single reference. Our key insight is that these legitimate variations primarily shift response typicality across the entire batch, whereas partial substitution injects individual responses that remain anomalous under the claimed model. Building on this, we introduce API-TAIL, a typicality audit that first absorbs batch-level shifts by aligning a single effective temperature to center standardized surprisal scores across the audited batch, and then flags the endpoint if the number of remaining tail responses exceeds a threshold calibrated across legitimate configurations. Evaluated on real-world commercial APIs, API-TAIL reliably controls false alarms across diverse honest providers while detecting even low-rate partial substitution with a small query budget, substantially outperforming existing rank- and MMD-based audits that lose detection power under the same composite calibration.

arXiv AI Papershace 17 días

Language Models Keep Abandoned Analyses: Residue and Adaptation after Garden-Path Sentences

Reading "While the man hunted the deer ran into the woods" requires giving up the analysis in which "the deer" is the object of "hunted". People who have just read such a sentence still produce more transitive structures, so the abandoned analysis primes later language. We ask whether language models keep using an analysis they have abandoned, and what in the model carries it. In 24 open models from 124M to 70B parameters, a garden-path sentence leaves two traces in the context. A residue of the abandoned analysis raises later object attachment, by about three quarters of the effect of a sentence in which the noun phrase really is an object, and it appears in sampled text, on held-out and human-normed items and for a second type of garden path. An adaptation toward the resolved structure scales with the sentence's disambiguation error and acts mainly on comprehension-like measures. Activation patching separates the two. Later text reads the residue from the role information in the noun phrase's states, which were computed under the object analysis before the disambiguation, and replacing these states removes almost all of the residue in the 32B and 70B models. The adaptation is read from the states that processed the disambiguation. Overridden statements show the same persistence (a corrected value keeps pulling later predictions in 8 of 9 models), and in most models the pull is carried by the positions after the statement. Finally, the human paradigm transfers only with controls for punctuation, because the models also write garden-path sentences themselves, which reverses the paradigm's raw statistic.

arXiv AI Papershace 17 días

Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training

Test-time training (TTT) enables a deployed language model to internalize incoming context on-the-fly into a small set of fast-weight parameters, rather than merely treating it as transient context for attention. In-Place TTT recently made this idea practical for large language models by repurposing the down-projection of standard MLP blocks as fast weights. However, we find that its benefit largely disappears on realistic web long-context question answering. We attribute this to In-Place TTT's uniform write schedule: every chunk is written with equal strength, so irrelevant content dilutes query-relevant information in fast-weight memory. Building on this insight, we propose Select-TTT, a model-agnostic, query-conditioned rule for In-Place TTT that scales each chunk's write strength by its relevance to the user query. This relevance signal requires no supervision and no new parameters: it is read directly from the model's frozen output head, as the probability mass that a chunk's hidden states assign to the query tokens. A temperature-scaled softmax turns these scores into learning-rate multipliers, leaving the chunk-wise, context-parallel computation of In-Place TTT intact. Select-TTT consistently improves long-context question answering on two benchmarks and two backbones. These findings highlight the value of query-conditioned fast weight writes for practical test-time training on long-context question answering, which is also potentially promising for long-horizon agent tasks involving multiple user queries over evolving contexts.

Hacker News (AI)hace 17 días

How I made it possible to pretrain a 1B LLM on 6GB VRAM

en▲ 5

GitHub Releases (AI inference)hace 17 días

transformers Release: v5.21.0

Release v5.21.0 New Model additions MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model. It is specialized for reading text-dense images such as scanned pages, screenshots, receipts and tables. Links: [Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/minicpm_ocr) | [Paper](https://huggingface.co/papers/2509.18154) Feat test (49920) by @guarin…

arXiv AI Papershace 17 días

Retriever-Free Retrieval: Navigating Documents with Decision Models

While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.

arXiv AI Papershace 17 días

Auto-Research Arena: Benchmarking and Advancing Auto-Research in Language Modeling

As autonomous research systems become more capable, benchmarks must both evaluate their performance and support meaningful research progress. We introduce Auto-Research Arena, a multi-target benchmark for evaluating autonomous research systems and discovering ideas in language modeling. Arena supports diverse research objectives within a shared experimental environment by separating admissibility from improvement: model quality and resource constraints determine whether a result qualifies, while the selected target measures progress among admissible results. We instantiate Arena in language model pretraining with nine targets spanning model, data, training, and inference efficiency, and evaluate seven research harnesses using two foundation models. Arena clearly differentiates existing harnesses across research objectives, with several sophisticated methods outperformed by our simple sequential search baseline, indicating substantial headroom in current auto-research systems. Beyond evaluation, Arena reveals a substantially broader frontier of model and system ideas aligned with active research directions. Reusing these discoveries in a new quality-driven search yields lower training loss under matched data and FLOPs and lower held-out BPB at the same model size. Together, Arena provides a common framework for benchmarking autonomous research and expanding its scope in language modeling. The code is available at https://github.com/Auto-Research-Arena/auto-research-arena

arXiv AI Papershace 17 días

Patient-specific rubric-based evaluation of large language models across longitudinal cancer care

Large language models (LLMs) show promise in specialty medicine, yet existing evaluations largely focus on isolated clinical encounters rather than tracking how clinical responsibilities evolve across a longitudinal care pathway. Here we introduce NPC-RubricBench, a phase-aware benchmark for evaluating multistage clinical reasoning across the cancer care continuum, using nasopharyngeal carcinoma as a defined disease context. Curated from longitudinal records of 405 patients across two cancer centers, the benchmark comprises 941 patient-phase units across six sequential care phases and 17,688 patient-specific atomic criteria spanning five evaluation dimensions, with each assessment strictly restricted to decision-time clinical evidence. Evaluating 30 general-purpose and medical LLMs revealed that strong diagnostic performance does not carry over to downstream care. We evaluated 30 general-purpose and medical LLMs, showing that high diagnostic performance did not translate into improved downstream care. Instead, the dominant failure modes reversed across phases. Explicit decision errors dominated anatomical staging at 48.2%, whereas decision omissions dominated initial work-up and post-treatment follow-up at 33.4% and 30.4%, respectively. In the evaluated model set, medically adapted models showed higher omission rates than general-purpose models. Moreover, varying query granularity exposes a critical specification trade-off: broad open-ended requests degrade Decision Quality across all 30 models, while more detailed, checklist-like prompts raise Decision Quality but reduce Evidence Faithfulness and Safety Adherence. Furthermore, NPC-RubricBench demonstrates that static diagnostic benchmarks are insufficient to ensure consistent clinical reliability over time, highlighting the importance of phase-adaptive safeguards in multistage medical AI.