Empresa

DeepSeek

70documentos

6últimos 7 dias

Atualizadoanteontem

EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture has demonstrated the potential to decouple factual knowledge storage from general-purpose computation, offering a promising route to updating factual knowledge while keeping the Transformer backbone fixed. Realizing this potential is challenging because different expressions of a fact may activate different n-gram embeddings, while updating shared embeddings can unintentionally change the model's predictions about other facts. We propose EngramEdit for decoupled knowledge updates through conditional memory. EngramEdit first computes target memory representations that make the model predict the updated fact across multiple expressions. It then jointly updates the shared n-gram embeddings to match these targets across expressions and edits, penalizing updates to frequently reused embeddings more strongly to preserve unrelated knowledge. Experiments show that EngramEdit enables independent factual knowledge updates through conditional memory, achieving near-perfect editing success. Revised knowledge is usable across unseen expressions and in multi-hop reasoning, with nearly three times the strongest baseline's accuracy under chain-of-thought (CoT) prompting. Unrelated knowledge and general capabilities are largely preserved even as factual updates accumulate. These findings show that EngramEdit turns conditional memory into an editable knowledge interface, extending its role beyond model scaling to support decoupled knowledge updates.

arXiv AI Papershá 4 dias

BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models

Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers can yield imbalanced expert utilization and treat experts as an unstructured collection, whose indices carry no topological meaning. We introduce {BRANCH-MoE}, a routing architecture that places (E) experts at the leaves of a binary decision tree of depth (_2 E). At each internal node the branching probability is centered on the arrival-weighted mean score of the traffic reaching that node. This mean is estimated using an exponential moving average, which promotes utilization of both child subtrees without an auxiliary load-balancing loss. We show that this moving-average estimate admits an explicit noise-lag trade-off. We prove that for linear node maps and log-concave arrival distributions, this mechanism prevents routing-mass collapse. We further establish that, under a frozen router, an expert's execution frequency controls its stochastic-gradient convergence rate, and that confident decisions near the root bound cross-device communication when experts are assigned to devices by tree prefix. We evaluate BRANCH-MoE against Switch softmax, DeepSeek-V3 dynamic-bias, Skywork logit-normalized, and deterministic hash routing on Criteo click-through-rate prediction, Forest Covertype, HIGGS, and YearPredictionMSD, using (E=16), top-(4) routing, and five random seeds. Our results show that hierarchical routing can preserve task quality and balanced utilization while inducing a topology that supports localized expert co-activation and reduced communication.

arXiv AI Papershá 5 dias

Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation

Agentic leaderboards increasingly evaluate systems on public benchmarks whose task statements and solution-bearing artifacts can remain accessible. We propose a measurement-first audit framework that distinguishes contamination claims according to the evidence required to support them. It separates three channels that require different evidence: training-time exposure, evaluation-time retrieval, and pipeline/scaffold leakage. Each channel is coded as open, partial, closed, or unknown under a fail-closed rule. Across nine Holistic Agent Leaderboard (HAL) configurations, none of the 27 channel assessments was coded closed, but incidents were confirmed in four configurations. We then apply the behavioral component of the framework to a reported file-localization gap on SWE-bench Verified, using an outcome-blind, same-repository matched-control design with symmetric prompt-leakage screening, paired and repository-aware uncertainty analyses, and scorer validation, evaluated on GPT-4.1 and DeepSeek-V4-Flash. Among the 100 pairs retained after symmetric screening and the pair-integrity exclusion, GPT-4.1 showed a +10.0-point pair-weighted Top-3 benchmark-associated gap, but the 95\% intervals from both the prespecified paired-bootstrap procedure and the post-hoc repository-balanced analysis included zero, leaving the benchmark-associated gap inconclusive. The reproduction scorer did not pass its validation gate: against consensus human labels, sufficient scorer sensitivity could not be established for either model, and both DeepSeek-V4-Flash firings on correct-gold comparisons were false positives. Without provenance evidence, appropriate controls, symmetric leakage screening, and validated scorers, stronger contamination claims are not warranted. The results do not establish training-data membership, contamination prevalence, or benchmark-induced score inflation.

arXiv AI Papershá 5 dias

CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training

Mixture-of-Experts (MoE) has been widely adopted in recent large language model (LLM) architectures. However, scaling up MoE in LLM training introduces system-level challenges on training, where non-uniform token routing can lead to highly imbalanced workloads across experts and devices, further destabilizing the training process. With trillion-scale LLMs, imbalanced expert workloads further amplify the resource cost of MoE training, resulting in degraded training efficiency and hardware utilization for underloaded experts, while hot experts require additional resources to accommodate excessive workloads. Recent studies address imbalanced MoE training through intricate parallelism strategies or resource reallocation. However, these system-level approaches often introduce additional resource requirements and considerable orchestration complexity, which become increasingly difficult to afford when training trillion-parameter LLMs under constrained computational resources. This work introduces CIPHER-MoE, which mitigates MoE workload imbalance while keeping the router's token-side Top-K selection unchanged. CIPHER-MoE applies affinity-aware Expert-to-Token filtering with explicit capacity control to reduce hotspot expert workloads without additional hardware resources or complex runtime design. The proposed method has been evaluated on large-scale MoE models, including DeepSeek-V4-Pro, showing up to 64.9 percentage points Top-1 expert workload reduction and 1.10-1.94training acceleration, while preserving the training quality. The source code will be released soon.

arXiv AI Papershá 6 dias

RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair

Large language model (LLM) agents increasingly reuse prior experience, but most approaches assume that problems and solutions are already aligned. Software histories rarely provide this alignment: a pull request (PR) may contain multiple continuous integration (CI) problems, failed attempts, reverted edits, and unrelated changes, obscuring which changes resolve each problem. We present RETRACE, a framework for reconstructing problem-level repair experience from such histories. RETRACE combines an endpoint view that reasons backward from changes retained in the passing revision with a development view that traces repair evolution forward through commit history. CI execution evidence reconciles the two views, and the recovered experience is represented at three abstraction levels, from concrete fixes to transferable repair patterns. For new failures, RETRACE retrieves relevant problem-level experience to guide repair. On CI-REPAIR-BENCH, comprising 565 PR-level repairs from 101 repositories across 12 failure categories, RETRACE improves mini-SWE-agent Pass@1 from 19.6% to 31.9% with MiniMax-M2.5 and from 23.3% to 32.8% with DeepSeek-V4-Flash. On a matched subset, Codex improves from 15.5% to 27.5%. Combining both views consistently outperforms either alone, showing that recovering problem-change alignment enables historical CI repairs to serve as reusable repair experience.

arXiv AI Papershá 6 dias

LatentIndex: Cross-Layer Sharing with Layer-Specific Selection for Sparse Attention

Sparse attention reduces core-attention computation, but its indexers still incur repeated selection work and per-layer key-cache storage. Reusing selected indices across layers reduces this overhead but constrains multiple layers to the same token set. We introduce LatentIndex, which extends the latent-sharing principle of Multi-head Latent Attention across indexer layers. Each layer group constructs a shared latent cache from its first layer's hidden states, while layer-specific scoring enables independent token selection. Absorbing key decoders into queries enables direct scoring of the shared cache without reconstructing historical per-layer keys. We develop training-free calibration and investigate a training-aware instantiation of this principle. To balance quality and computation, a hierarchical selection (HS) variant lets followers independently refine a shared candidate set proposed by the anchor. With four-layer sharing, LatentIndex reduces logical indexer-cache storage by 61.1% on DeepSeek-V3.2. Across DeepSeek-V3.2 and GLM-5, training-free LatentIndex improves head-wise attention-mass recall over IndexCache by up to 3.28 percentage points while maintaining RULER and LongBench performance close to native DSA. HS further achieves 2.30-2.72 times decode indexer speedups over DSA across 8K-128K contexts, retaining most of LatentIndex's recall. LatentIndex offers a new perspective on cross-layer indexing: sharing continuous representations rather than discrete selections enables efficient reuse while preserving layer-specific token selection.

arXiv AI Papershá 7 dias

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources. Existing benchmarks leave gaps in executable coverage of their runtime security risks, while evolving model capabilities, harnesses, tools, and threats motivate benchmark evolution. We introduce EvoRiskBench, an evolving benchmark organized around the EP-Path-EF framework, which links an initial risk entry point to a one-hop technical effect through an agent-mediated risk path. The framework defines nine entry-point categories and five effect categories; a 20-participant study supports their interpretability and classification consistency on representative cases. Guided by this framework, an automated end-to-end workflow constructs and executes risk cases in isolated environments and independently verifies outcomes using runtime traces and environment states. The benchmark provides a reproducible dataset of 450 adversarial tasks across six scenarios. We evaluate nine model-harness configurations spanning three models (GPT-5.6 Sol, DeepSeek-V4-Pro-0813, and Claude Opus 5) and three harnesses (Claude Code, Codex, and OpenClaw). Our results reveal substantial vulnerabilities across systems. The most vulnerable configuration, Codex with DeepSeek-V4-Pro-0813, reaches a 68.44% attack success rate (ASR), indicating that configuration of workspace agent is insufficient to ensure secure autonomous execution. ASR varies more across models than harnesses, and harness differences depend on the model. The benchmark cases and evaluation platform will be released after completion of artifact safety and reproducibility checks.

arXiv AI Papershá 10 dias

ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control

Scaling Large Language Models (LLMs) via Mixture-of-Experts (MoE) enables massive parameter growth with nearly constant per-token computation. However, further scaling the parameter count requires increasingly sparse routing, where expert load imbalance becomes more severe. This imbalance reduces parameter utilization and training efficiency, and can undermine training stability, becoming a bottleneck to reliable scaling. In this work, we unify two representative auxiliary-loss-free methods as incomplete Proportional-Integral-Derivative (PID) controllers: DeepSeek's loss-free method acts as a fixed-step integral controller, while Kimi K3's Quantile Balancing functions as a generalized proportional controller. Building on this control perspective, we propose ID Balancing, an Integral-Derivative controller. It scales its integral term with load error and activates its derivative term only when imbalance worsens, enabling stronger corrections for large or worsening errors and smaller updates near balance. Evaluated across Top-10, Top-5, and Top-3 routing over 768 experts, ID Balancing reduces worst-case backbone MaxVio and training-average backbone MinVio by over 50\% and 12\%, respectively, relative to the best baselines in the Top-3 setting. When the total parameter count increases from 18.9B to 69.9B (Top-10-of-768), ID Balancing's worst-case backbone MaxVio remains nearly unchanged and is approximately 89.6\% lower than that of the auxiliary-loss baseline. ID Balancing also maintains competitive language-modeling and downstream performance. The advantages of ID Balancing grow as sparsity increases, making it a promising solution for scaling larger, sparser MoE models.

arXiv AI Papershá 10 dias

Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs

As the chain-of-thought reasoning capabilities of large language models improve, evaluating and calibrating their reasoning confidence is becoming increasingly important for quantifying the uncertainty of their answers. Current methods for estimating the confidence of large language models are generally based on probabilities of selected key tokens, but the underlying mechanism remains unclear. Our pilot study finds that replacing selected token probabilities with coarse substitutes can also improve calibration, motivating us to further explore effective signals of model confidence. We introduce Divergent Token Confidence (DTC), a framework that estimates confidence by counting tokens at which two models strongly disagree during decoding. DTC identifies these divergent tokens using the Jensen-Shannon divergence between next-token distributions evaluated along the same reasoning trajectory. We find that their count is almost negatively associated with answer accuracy, thereby serving as a simple yet effective signal for uncertainty quantification. DTC supports both white-box and black-box evaluation using auxiliary models, without explicit training and affecting the generation process. Experiments across multiple model families and six mathematical benchmarks demonstrate improved calibration over probability-based and verbalized baselines. Under white-box evaluation, the count-only estimator achieves an average expected calibration error of 13.0%, compared with 32.7%-42.4% for standard full-sequence confidence methods. In black-box settings, it also improves calibration over the original verbalized scores. For example, mean expected calibration error falls from 32.1%-40.2% to 13.7%-16.3% on DeepSeek-V3.2. These findings provide new insights for improving reasoning uncertainty quantification in large language models. The code is released at https://github.com/szu-tera/DTC.git.

The Verge AIhá 10 dias

Will Chinese AI companies slow down? A top House Democrat wants answers

As President Donald Trump prepares to meet tech and AI CEOs in Washington, Rep. Ro Khanna (D-CA) is calling for a treaty between the US…

AWS Machine Learning Bloghá 14 dias

Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput

Learn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Amazon S3 and increased aggregate reinforcement learning rollout throughput by 40% for large-scale RLHF and GRPO training.

Hacker News (AI)há 14 dias

DeepSeek beats GPT-6 Sol in autonomous drug development

nl▲ 5

arXiv AI Papershá 15 dias

Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs

Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e., an output prefix, then all subsequent tokens will be conditioned on it. This output-prefix attack technique is a cheap black-box prompt injection. Prior work has shown this type of attack can reliably jailbreak non-reasoning models. Most reasoning models add an intermediate scratchpad reasoning step before the assistant's final response. The ability to edit this reasoning channel is exposed by some APIs and attack vectors can be leveraged for reasoning injection attacks. We present the first systematic, controlled study that isolates the scratchpad reasoning channel as an output-prefix attack vector, and the first to compare reasoning-only, output-prefix-only and reasoning-plus-output-prefix attacks across both exposed- and hidden-reasoning models. Using a factorial design of 3 prefix types 2 reasoning injections over 1{,}800 test cases drawn from AdvBench, we attack three 2026-era frontier models Gemini 3 Flash Preview, DeepSeek V4 Flash, and Claude Haiku 4.5. We find that injecting malicious reasoning alone is essentially inert (0\% attack success), but injecting the same reasoning together with a trivial output prefix raises the attack success rate to as high as 99\% for some models. For this type of attack we find that contextual prefixes work better than static prefixes; and that susceptibility is dependent on the model.

arXiv AI Papershá 15 dias

Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?

Recent studies have shown that Large Language Models can effectively solve problems and fix bugs in diverse programming environments, including competitive programming. Existing approaches primarily evaluate LLM performance in problem solving or bug fixing independently, but do not explore the relationship between these two capabilities. This work focuses on determining how much the LLM deviates from a buggy solution to fix the bug compared to a human-written patch, and if there is a bias towards generating entirely new solutions. We construct a dataset with all the submissions (3000) from a couple of users from Codeforces, and we match each buggy submission with its corresponding human fix. By using the similarity between the buggy solution and the human fix as a baseline, we evaluate the quality of LLM-generated bug fixes on 3 OpenAI GPT models (gpt-5-nano, gpt-5-mini, gpt-5.1). We check if the generated solutions solve the problem by using the Codeforces-R1 dataset, an openly available dataset that has tests generated with the DeepSeek-R1 model. Our findings suggest that LLMs tend to modify more lines than necessary compared to human fixes and, in some cases, generate entirely new solutions. We also observe that LLMs solve more problems correctly when allowed to generate solutions from scratch rather than patch buggy submissions, even when those submissions are close to the human patch. This has important implications for the design of AI-assisted programming tools, particularly in supporting user debugging processes and promoting incremental problem-solving strategies rather than solution replacement.

arXiv AI Papershá 16 dias

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather than internalized as reusable model capabilities. We introduce SkillGym, a framework that transforms these skills into executable, verifiable training environments for large language model agents. Its skill-to-task pipeline instantiates concrete tasks, verifies outcomes with code-based checkers, and assesses empirical skill dependence through contrastive executions. We construct and release 2,756 environments across 12 categories and collect 8,364 successful trajectories from multiple models and harnesses, averaging 49 tool calls and over 60k logged text tokens. These resources support supervised fine-tuning on verified workflows and reinforcement learning with outcome-based rewards. Under Claude Code, supervised fine-tuning improves Qwen3.5-35B-A3B by 199 Elo on GDPval-AA v2, 19.10 percentage points on Terminal-Bench 2.1, and 28.13 and 12.38 points on SkillsBench v1.1 with and without skills, respectively. Our 35B SkillGym-Agent reaches 51.47\% on skill-assisted SkillsBench, exceeding reported scores for Claude Sonnet 4.6, GPT-5.4 Mini, and DeepSeek V4 Pro. Without skills, it also surpasses skill-assisted bases under Codex and Claude Code, suggesting reusable procedural competence.

arXiv AI Papershá 17 dias

MWE-ECL: Recoverable Long-Range Context Does Not Always Override Local Lexical Priors

Long-context evaluations often test whether a model can recover distant evidence, but recoverability does not guarantee behavioral influence. We test the prediction that a distant discourse anchor can remain explicitly recoverable yet fail to change the locally preferred reading of a familiar multiword expression; such failures should concentrate when the model's no-anchor default conflicts with the anchor, while prior-correct decisions remain largely preserved. We introduce Multiword Expression Effective Context Length (MWE-ECL), a bilingual diagnostic whose matched anchor-retrieval, no-anchor prior, and interpretation prompts measure explicit recoverability, model-observed defaults, and anchor-conditioned decisions, respectively. Across eight English deployment panels on a shared 0-128K grid, retrieval-control accuracy on prior-conflict items is 0.989-1.000, prior-conflict override spans 0.806-1.000 (0.809-1.000 after conditioning on correct retrieval), and preservation of prior-correct decisions remains 0.977-1.000. A same-call control querying retrieval and interpretation in one prompt reproduces the gap for DeepSeek V4 Pro (1.000 retrieval versus 0.900-0.920 interpretation), showing that separate invocations are not its sole explanation; smaller or absent gaps in the other two models bound its generality. For DeepSeek V4 Flash, separate prompt-fit tests retain perfect retrieval with lower interpretation at 512K and 1M, while foil-consistent cues shift the no-anchor prior far more than retrieval; cross-model cue effects are heterogeneous. A separately reported 10-family Chinese subset shows similar descriptive gaps, but imperfect retrieval for some models prevents an integration-only attribution. MWE-ECL therefore evaluates whether explicitly recoverable distant context changes a competing local semantic decision.

arXiv AI Papershá 20 dias

Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics

Reasoning language models are trained to produce solutions, not to refuse them, and this bias persists when the problem they are handed is false. Asked to prove a corrupted theorem, a strong model will typically comply and produce a confident derivation of something untrue. We present Euston, an 8B mathematical claim-verification model trained to resist exactly this. Training data were generated with GraphSynth, a probabilistic factor-graph generator that couples attribute-level diversity to decode-time structural masking and span-synchronized verification, yielding 3{,}026 matched true/corrupted statement pairs (6,052 statements) drawn from arXiv papers spanning 2010--2025. We fine-tuned DeepSeek-R1-8B with GRPO under a rule-based, zero-API reward for 189 steps on four H100 GPUs. On a balanced 200-true/200-false held-out split, balanced accuracy rises from 29.50% to 63.75% and the discrimination gap---the difference between the rate of calling false statements false and the rate of calling true statements false moves from -0.5% (z=-0.1) to +27.5% (z=+6.0). Critically, the gain is not purchased with general mathematical ability: AIME 2026 accuracy under official semantics is 65.00% against a 69.17% base, a difference of -4.17% that is not statistically significant, whereas an earlier run of the same recipe on a smaller GraphSynth corpus collapsed to 40.00%. Median response length also falls from 19,217 to 18,296 tokens and the truncation rate from 25.8% to 8.3%, so the improvement does not come from thinking longer. We report the result together with the confounds that bound its interpretation, principally the all-false composition of the official evaluation sets and the low precision implied at realistic error prevalence.

Hugging Face New Modelshá 20 dias

drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed

New image-text-to-text model. Tags: deepseek, deepseek-v4.1, deepseek-v4.1-flash, abliterated, uncensored, cybersecurity, moe, fp8

en♥ 118

Hugging Face New Modelshá 20 dias

jinaai/jina-ocr-v1

New image-text-to-text model. Tags: deepseek_vl_v2, feature-extraction, multimodal, multilingual, ocr, vision-language, document-intelligence, image-text-to-text

en♥ 99

AWS Machine Learning Bloghá 21 dias

Introducing Kimi K3 on Amazon Bedrock

Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and explicit prompt caching to reduce latency and input costs.