Skip to main content
Search

Northeastern University

23 related articles

Subscribe to updates
  1. Phones and cloud split generative inference: MAGS bids instead of stampeding, cutting p99 latency 17.1%

    A generative query's cost is unknown until the answer is written, so devices reserve resources blind and many crowd one server at once. MAGS has each device forecast token count and generation entropy with a four-layer probe on its local model, then bid for cloud capacity against a broadcast congestion price, choosing its per-token privacy parameter in the same bid. Over ten seeds it cuts p99 latency 17.1%, energy per token 13.6% and raises throughput 20.7% against a reactive PPO baseline given identical observations; an eight-device, two-server testbed drops the cross-device correlation of offload decisions from 0.41 to 0.08.

  2. arXiv

    JEPA world models can memorize backgrounds and forget actions: motion-guided contrastive regularization lifts planning success from 52% to 78% under randomized backgrounds

    When a JEPA-style world model is regularized only through its embedding distribution, the encoder can treat the fixed background of each episode as its main content and suppress the state changes produced by robot-object interaction, a failure the authors call static collapse. The new method contrasts the predicted latent transition with transitions to other observations from the same episode, and uses optical-flow similarity as soft targets so candidates with similar motion receive similar supervision. Planning success rises from 52% to 78% over LeWM on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while four other visual-control benchmarks stay comparable.

  3. arXiv

    One corrupted detector out of four drops LLM investigators to 0.50–0.72 accuracy: CAV rechecks claims against evidence the tools cannot touch

    On the corrected CIC-IDS2017 dataset, when labels and confidences from four heterogeneous detectors are corrupted under a threat model, unverified open-weight LLM investigators fall to 0.50–0.72 accuracy with one corrupted detector and to 0.13 or less with three. Conflict-Aware Evidence Verification (CAV) keeps reported confidences out of the vote and, only when tools conflict, tests the leading candidates with a nearest-neighbour trust score computed from raw traffic features. With its prompt frozen before testing, CAV-LLM reaches 0.84–0.88 under three corrupted detectors in both persistent and sporadic scopes, against at most 0.08 for the naive investigator, while calling the LLM on 0.4% of clean traffic.

  4. arXiv

    SAM 3 at 4-bit weights stops grabbing the wrong object: SPQ lifts RefCOCO hit rate from 42.1 to 72.5

    Quantizing SAM 3's image-encoder weights to 4 bits while keeping activations at 8 bits produces prompt-alignment drift: masks look plausible but land on the wrong object or lose the target across video frames. SPQ gives more calibration weight to parameters that affect text-concept scores, constrains feature error along low-variance residual directions, and folds a mean-error correction estimated from paired video rollouts into existing biases. Under W4A8, RefCOCO Pr@0.5 rises from 42.1 for PTQ4SAM to 72.5 while retaining 54.8 COCO mask AP, with no added inference operators.

  5. arXiv

    Where to inject activation steering: TopoSteer ranks layers by the connectivity length of displacement clouds, skipping held-out trials

    Activation steering adds a vector to a large language model's internal representations at inference time, but where to add it has mostly been settled by trial: existing selectors score how separable the two activation classes are or how well individual displacements align with their mean, without ever steering the model to check. TopoSteer instead scores each layer by the total length of the Euclidean minimum spanning tree of its per-example displacement cloud, measuring whether the mean-difference vector can stand in for those displacements. Across five instruction-tuned models and six binary persona-steering tasks it beats LayerNavigator in most model-budget comparisons, but the margin depends on model and layer budget and is smaller and more mixed on Qwen-7B and Qwen-32B.

  6. arXiv

    No weight updates at inference: steering neurons per query lifts seven models from 3B to 32B

    Instead of a fixed intervention chosen in advance, Q-NeuS reads each query's own internal activations to decide which feed-forward neurons to amplify, improving every one of seven models from 3B to 32B parameters across three benchmarks.

  7. arXiv

    Terminal agents build their own RL environments: up to 25x more valid ones, 75% cheaper each

    AutoEnvScaling turns reinforcement-learning environment design into a terminal task, letting a proposer agent build new environments from the solver's rollouts, raising the valid-environment rate by up to 25 times and cutting cost per valid environment by up to 75%.

  8. arXiv

    MiniCorp lets an agent firm run an e-commerce company: price elasticities of 2.9–3.2, 23–32% ad-attributed lift, and delayed organic gains

    MiniCorp is a closed-loop office simulator that couples a persistent agent firm with an evolving e-commerce external market: the external world explicitly models search demand, matching and ranking, click and conversion, sponsored-search auctions, and dynamic competitors, while the internal world is a firm of standing roles that read exported business data, communicate, and propose decisions. Experiments show the integrated market reproduces empirical response patterns in price elasticity, the persistent effects of temporary discounts and stockouts, and the delayed organic gains of advertising, and that agents coordinate across roles while generating replayable counterfactual enterprise data.

  9. arXiv

    ΔRepresentation models phenotypes as representation increments over normal anatomy via counterfactual reasoning, improving lesion grounding and phenotype recognition across six medical VLMs

    The work proposes ΔRepresentation, a visual phenotype representation learning framework for medical VLMs: BaseAnatomy applies geometry supervision to normal anatomical representations using ideal spatial distributions, while Phenotype uses counterfactual reasoning to estimate a normal anatomical reference for each pathological patch and learn phenotype-specific representation increments that cluster by phenotype. On ReXGroundingCT and LIDC-IDRI, it consistently improves lesion grounding and phenotype recognition across six pretrained medical VLMs.

  10. arXiv

    Researchers distinguish faithful from unfaithful self-reporting models via attribution similarity, 0.34 versus 0.08 on average

    In a controlled setting, the authors trained low-rank adapters to make binary decisions for fictitious characters according to latent linear preference functions, found that accurate self-reporting of learned preferences emerges from decision-task fine-tuning alone without explicit self-report supervision, and showed that faithful models have significantly higher attribution similarity between the decision and self-report tasks (mean 0.34 versus 0.08; paired-bootstrap 95% CI [0.16, 0.36]), allowing faithful and unfaithful self-report to be distinguished without understanding the report content.